WO2021071294A1

WO2021071294A1 - Method and device for transform-based image coding

Info

Publication number: WO2021071294A1
Application number: PCT/KR2020/013753
Authority: WO
Inventors: 구문모; 임재현; 김승환; 살레히파메흐디
Original assignee: 엘지전자 주식회사
Priority date: 2019-10-08
Filing date: 2020-10-08
Publication date: 2021-04-15

Abstract

An image decoding method according to the present document may comprise the steps of: deriving modified transform coefficients by applying LFNST to transform coefficients; deriving residual samples on a current block on the basis of inverse primary transform on the modified transform coefficients; and generating a reconstructed picture on the basis of the residual samples, wherein the LFNST is performed on the basis of an LFNST transform set, an LFNST kernel included in the LFNST transform set, and an LFNST index indicating the LFNST kernel, and a first bin and a second bin of a syntax element bin string for the LFNST index are decoded by a context coding scheme.

Description

Transform-based image coding method and apparatus therefor

This document relates to an image coding technology, and more particularly, to a transform-based image coding method and an apparatus therefor in an image coding system.

Recently, demand for high-resolution, high-quality video/video such as 4K or 8K or higher UHD (Ultra High Definition) video/video is increasing in various fields. As the image/video data becomes high-resolution and high-quality, the amount of information or bits to be transmitted increases relative to that of the existing image/video data. Therefore, the image data can be transmitted using a medium such as an existing wired/wireless broadband line or an existing storage medium. In the case of storing video/video data by using it, the transmission cost and storage cost increase.

In addition, interest and demand for immersive media such as VR (Virtual Reality) and AR (Artificial Realtiy) contents or holograms are increasing recently. Broadcasting for is on the rise.

Accordingly, a high-efficiency video/video compression technique is required to effectively compress, transmit, store, and reproduce information of high-resolution, high-quality video/video having various characteristics as described above.

The technical problem of this document is to provide a method and apparatus for increasing image coding efficiency.

Another technical problem of this document is to provide a method and apparatus for increasing the efficiency of LFNST index coding.

Another technical problem of this document is to provide a method and apparatus for increasing the efficiency of the second-order transformation through coding of an LFNST index.

According to an embodiment of the present document, a method for decoding an image performed by a decoding apparatus is provided. The method includes the steps of deriving a modified transform coefficient by applying LFNST to the transform coefficient; Deriving residual samples for the current block based on the inverse linear transform of the modified transform coefficients; And generating a reconstructed picture based on the residual samples, wherein the LFNST is performed based on an LFNST transform set, an LFNST kernel included in the LFNST transform set, and an LFNST index indicating the LFNST kernel, The first bin and the second bin of the syntax element bin string for the LFNST index may be decoded using a context coding method.

Deriving context information of a syntax element for the LFNST index; Decoding bins of a syntax element bin string for the LFNST index based on the context information; It may further include the step of deriving a value of the syntax element for the LFNST index.

Depending on the tree type of the current block, context information for the first bin may be derived as a different value.

If the tree type of the current block is a single tree, the first bin may be derived as first context information, and if the tree type of the current block is not a single tree, the first bin may be derived as second context information.

Regardless of the tree type of the current block, context information for the second bin may be derived with the same value.

The LFNST conversion set includes two LFNST kernels, and a value for the syntax element is 0 indicating a case where the LFNST is not applied to the current block, 1 indicating a first LFNST kernel among the LFNST kernels, It may include any one of 2 indicating a second LFNST kernel among the LFNST kernels.

The value for the syntax element is binarized into a truncated universal code, the value 0 for the syntax element is '0', the value 1 for the syntax element is '10', and the value 2 for the syntax element Can be binarized to '11'.

According to an embodiment of the present document, a video encoding method performed by an encoding device is provided. The method includes the steps of deriving a modified transform coefficient by applying LFNST to the transform coefficient; Encoding the LFNST index indicating the LFNST kernel used for the LFNST and quantized residual information, wherein the LFNST is performed based on the LFNST transform set and the LFNST kernel included in the LFNST transform set, The first bin and the second bin of the syntax element bean string for the LFNST index are encoded using a context coding method.

According to another embodiment of the present document, a digital storage medium in which encoded image information generated according to an image encoding method performed by an encoding apparatus and image data including a bitstream are stored may be provided.

According to another embodiment of the present document, a digital storage medium in which image data including a bitstream and encoded image information causing the decoding apparatus to perform the image decoding method may be provided.

According to this document, overall video/video compression efficiency can be improved.

According to this document, the efficiency of LFNST index coding can be improved.

According to this document, the efficiency of quadratic transformation can be improved through coding of the LFNST index.

The effects that can be obtained through a specific example of the present specification are not limited to the effects listed above. For example, there may be various technical effects that a person having ordinary skill in the related art can understand or derive from the present specification. Accordingly, specific effects of the present specification are not limited to those explicitly described in the present specification, and may include various effects that can be understood or derived from the technical features of the present specification.

1 is a diagram schematically illustrating a configuration of a video/video encoding apparatus to which the present document can be applied.

2 is a diagram schematically illustrating a configuration of a video/video decoding apparatus to which the present document can be applied.

3 schematically shows a multiple transformation technique according to an embodiment of the present document.

4 exemplarily shows intra directional modes of 65 prediction directions.

5 is a diagram for explaining an RST according to an embodiment of the present document.

6 is a diagram illustrating a sequence of arranging output data of a forward linear transformation into a one-dimensional vector, according to an example.

7 is a diagram illustrating a sequence of arranging output data of a forward quadratic transformation into 2D blocks according to an example.

8 is a diagram illustrating a block shape to which LFNST is applied.

9 is a diagram illustrating an arrangement of output data of forward LFNST according to an example.

10 is a diagram illustrating zero-out in a block to which 4x4 LFNST is applied according to an example.

11 is a diagram illustrating zero-out in a block to which 8x8 LFNST is applied according to an example.

12 is a diagram illustrating a block diagram of a CABAC encoding system according to an embodiment.

13 is a diagram for describing a method of decoding an image according to an example.

14 is a diagram for describing a method of encoding an image according to an example.

15 schematically shows an example of a video/video coding system to which this document can be applied.

16 exemplarily shows a structure diagram of a content streaming system to which this document is applied.

In this document, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit this document to a specific embodiment. Terms commonly used in this specification are used only to describe specific embodiments, and are not intended to limit the technical idea of this document. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or a combination thereof described in the specification, but one or more other features or It is to be understood that the presence or addition of numbers, steps, actions, components, parts, or combinations thereof does not preclude the possibility of preliminary exclusion.

Meanwhile, each of the components in the drawings described in the present document is independently illustrated for convenience of description of different characteristic functions, and does not mean that each component is implemented as separate hardware or separate software. For example, two or more of the configurations may be combined to form one configuration, or one configuration may be divided into a plurality of configurations. Embodiments in which each configuration is integrated and/or separated are also included in the scope of the rights of this document, unless departing from the essence of this document.

Hereinafter, exemplary embodiments of the present document will be described in more detail with reference to the accompanying drawings. Hereinafter, the same reference numerals are used for the same constituent elements in the drawings, and duplicate descriptions for the same constituent elements are omitted.

This document is about video/image coding. For example, the method/embodiment disclosed in this document is a VVC (Versatile Video Coding) standard (ITU-T Rec. H.266), a next-generation video/image coding standard after VVC, or other video coding related standards ( For example, it may be related to a High Efficiency Video Coding (HEVC) standard (ITU-T Rec. H.265), an essential video coding (EVC) standard, an AVS2 standard, etc.).

In this document, various embodiments of video/video coding are presented, and the above embodiments may be performed in combination with each other unless otherwise stated.

In this document, video may mean a set of images over time. A picture generally refers to a unit representing one image in a specific time period, and a slice/tile is a unit constituting a part of a picture in coding. A slice/tile may include one or more coding tree units (CTU). One picture may be composed of one or more slices/tiles. One picture may be composed of one or more tile groups. One tile group may include one or more tiles.

A pixel or pel may mean a minimum unit constituting one picture (or image). In addition,'sample' may be used as a term corresponding to a pixel. A sample may generally represent a pixel or a value of a pixel, may represent only a pixel/pixel value of a luma component, or may represent only a pixel/pixel value of a chroma component. Alternatively, the sample may mean a pixel value in the spatial domain, and when such a pixel value is converted to the frequency domain, it may mean a transform coefficient in the frequency domain.

A unit may represent a basic unit of image processing. The unit may include at least one of a specific area of a picture and information related to the corresponding area. One unit may include one luma block and two chroma (ex. cb, cr) blocks. The unit may be used interchangeably with terms such as a block or an area depending on the case. In general, the MxN block may include samples (or sample arrays) consisting of M columns and N rows, or a set (or array) of transform coefficients.

In this document, “/” and “,” are interpreted as “and/or”. For example, “A/B” is interpreted as “A and/or B”, and “A, B” is interpreted as “A and/or B”. Additionally, “A/B/C” means “at least one of A, B and/or C”. In addition, “A, B, C” also means “at least one of A, B and/or C”. (In this document, the term “/” and "," should be interpreted to indicate “and/or.” For instance, the expression “A/B” may mean “A and/or B.” Further, “A, B” may mean “A and/or B.” Further, “A/B/C” may mean “at least one of A, B, and/or C.” Also, “A/B/C” may mean “ at least one of A, B, and/or C.”)

Additionally, in this document “or” is interpreted as “and/or”. For example, “A or B” may mean 1) only “A”, 2) only “B”, or 3) “A and B”. In other words, “or” in this document may mean “additionally or alternatively”. (Further, in the document, the term “or” should be interpreted to indicate “and/or.” For instance, the expression “A or B” may comprise 1) only A, 2) only B, and/or 3) both A and B. In other words, the term “or” in this document should be interpreted to indicate “additionally or alternatively.”)

In the present specification, “at least one of A and B” may mean “only A”, “only B” or “both A and B”. In addition, in this specification, the expression “at least one of A or B” or “at least one of A and/or B” means “at least one It can be interpreted the same as “at least one of A and B”.

In addition, in the present specification, “at least one of A, B and C” means “only A”, “only B”, “only C”, or “A, B and C It can mean any combination of A, B and C”. In addition, “at least one of A, B or C” or “at least one of A, B and/or C” means It can mean “at least one of A, B and C”.

In addition, parentheses used in the present specification may mean “for example”. Specifically, when indicated as “prediction (intra prediction)”, “intra prediction” may be proposed as an example of “prediction”. In other words, “prediction” in the present specification is not limited to “intra prediction”, and “intra prediction” may be suggested as an example of “prediction”. In addition, even when indicated as “prediction (ie, intra prediction)”, “intra prediction” may be proposed as an example of “prediction”.

In the present specification, technical features that are individually described in one drawing may be implemented individually or at the same time.

1 is a diagram schematically illustrating a configuration of a video/video encoding apparatus applicable to embodiments of the present document. Hereinafter, the video encoding device may include an image encoding device.

Referring to FIG. 1, the encoding apparatus 100 includes an image partitioner 110, a predictor 120, a residual processor 130, an entropy encoder 140, and It may be configured to include an adder 150, a filter 160, and a memory 170. The prediction unit 120 may include an inter prediction unit 121 and an intra prediction unit 122. The residual processing unit 130 may include a transform unit 132, a quantizer 133, a dequantizer 134, and an inverse transformer 135. The residual processing unit 130 may further include a subtractor 131. The addition unit 150 may be referred to as a reconstructor or a recontructged block generator. The image segmentation unit 110, the prediction unit 120, the residual processing unit 130, the entropy encoding unit 140, the addition unit 150, and the filtering unit 160 described above may include one or more hardware components ( For example, it may be configured by an encoder chipset or a processor). In addition, the memory 170 may include a decoded picture buffer (DPB), and may be configured by a digital storage medium. The hardware component may further include the memory 170 as an internal/external component.

The image segmentation unit 110 may divide an input image (or picture, frame) input to the encoding apparatus 100 into one or more processing units. For example, the processing unit may be referred to as a coding unit (CU). In this case, the coding unit is recursively divided according to the QTBTTT (Quad-tree binary-tree ternary-tree) structure from a coding tree unit (CTU) or a largest coding unit (LCU). I can. For example, one coding unit may be divided into a plurality of coding units of a deeper depth based on a quad tree structure, a binary tree structure, and/or a ternary structure. In this case, for example, a quad tree structure may be applied first, and a binary tree structure and/or a ternary structure may be applied later. Alternatively, the binary tree structure may be applied first. The coding procedure according to this document may be performed based on the final coding unit that is no longer divided. In this case, based on the coding efficiency according to the image characteristics, the maximum coding unit can be directly used as the final coding unit, or if necessary, the coding unit is recursively divided into coding units of lower depth to be optimal. A coding unit of the size of may be used as the final coding unit. Here, the coding procedure may include a procedure such as prediction, transformation, and restoration, which will be described later. As another example, the processing unit may further include a prediction unit (PU) or a transform unit (TU). In this case, the prediction unit and the transform unit may be divided or partitioned from the above-described final coding unit, respectively. The prediction unit may be a unit of sample prediction, and the transform unit may be a unit for inducing a transform coefficient and/or a unit for inducing a residual signal from the transform coefficient.

The unit may be used interchangeably with terms such as a block or an area depending on the case. In general, the MxN block may represent a set of samples or transform coefficients consisting of M columns and N rows. In general, a sample may represent a pixel or a value of a pixel, may represent only a pixel/pixel value of a luminance component, or may represent only a pixel/pixel value of a saturation component. Sample may be used as a term corresponding to one picture (or image) as a pixel or pel.

The encoding apparatus 100 subtracts the prediction signal (predicted block, prediction sample array) output from the inter prediction unit 121 or the intra prediction unit 122 from the input video signal (original block, original sample array) to make a residual. A signal (residual signal, residual block, residual sample array) may be generated, and the generated residual signal is transmitted to the converter 132. In this case, as illustrated, a unit that subtracts the prediction signal (prediction block, prediction sample array) from the input video signal (original block, original sample array) in the encoding apparatus 100 may be referred to as a subtraction unit 131. The prediction unit may perform prediction on a block to be processed (hereinafter referred to as a current block) and generate a predicted block including prediction samples for the current block. The prediction unit may determine whether intra prediction or inter prediction is applied in units of a current block or CU. The prediction unit may generate various information related to prediction, such as prediction mode information, as described later in the description of each prediction mode, and transmit it to the entropy encoding unit 140. The information on prediction may be encoded by the entropy encoding unit 140 and output in the form of a bitstream.

The intra prediction unit 122 may predict the current block by referring to samples in the current picture. The referenced samples may be located in the vicinity of the current block or may be located away from each other according to the prediction mode. In intra prediction, prediction modes may include a plurality of non-directional modes and a plurality of directional modes. The non-directional mode may include, for example, a DC mode and a planar mode (Planar mode). The directional mode may include, for example, 33 directional prediction modes or 65 directional prediction modes according to the degree of detail of the prediction direction. However, this is an example, and more or less directional prediction modes may be used depending on the setting. The intra prediction unit 122 may determine a prediction mode applied to the current block by using the prediction mode applied to the neighboring block.

The inter prediction unit 121 may derive a predicted block for the current block based on a reference block (reference sample array) specified by a motion vector on the reference picture. In this case, in order to reduce the amount of motion information transmitted in the inter prediction mode, motion information may be predicted in units of blocks, subblocks, or samples based on a correlation between motion information between a neighboring block and a current block. The motion information may include a motion vector and a reference picture index. The motion information may further include inter prediction direction (L0 prediction, L1 prediction, Bi prediction, etc.) information. In the case of inter prediction, the neighboring block may include a spatial neighboring block existing in the current picture and a temporal neighboring block existing in the reference picture. The reference picture including the reference block and the reference picture including the temporal neighboring block may be the same or different. The temporal neighboring block may be referred to as a collocated reference block, a collocated CU (colCU), and the like, and a reference picture including the temporal neighboring block may be referred to as a collocated picture (colPic). May be. For example, the inter prediction unit 121 constructs a motion information candidate list based on neighboring blocks, and provides information indicating which candidate is used to derive a motion vector and/or a reference picture index of the current block. Can be generated. Inter prediction may be performed based on various prediction modes. For example, in the case of a skip mode and a merge mode, the inter prediction unit 121 may use motion information of a neighboring block as motion information of a current block. In the case of the skip mode, unlike the merge mode, a residual signal may not be transmitted. In the case of motion vector prediction (MVP) mode, the motion vector of the current block is determined by using a motion vector of a neighboring block as a motion vector predictor and signaling a motion vector difference. I can instruct.

The prediction unit 120 may generate a prediction signal based on various prediction methods to be described later. For example, the prediction unit may apply intra prediction or inter prediction to predict one block, as well as simultaneously apply intra prediction and inter prediction. This can be called combined inter and intra prediction (CIIP). In addition, the prediction unit may be based on an intra block copy (IBC) prediction mode or a palette mode for prediction of a block. The IBC prediction mode or the palette mode may be used for content image/video coding such as a game, such as, for example, screen content coding (SCC). IBC basically performs prediction in the current picture, but can be performed similarly to inter prediction in that it derives a reference block in the current picture. That is, the IBC may use at least one of the inter prediction techniques described in this document. The palette mode can be viewed as an example of intra coding or intra prediction. When the palette mode is applied, a sample value in a picture may be signaled based on information about a palette table and a palette index.

The prediction signal generated through the prediction unit (including the inter prediction unit 121 and/or the intra prediction unit 122) may be used to generate a reconstructed signal or may be used to generate a residual signal. The transform unit 132 may generate transform coefficients by applying a transform technique to the residual signal. For example, the transformation technique uses at least one of DCT (Discrete Cosine Transform), DST (Discrete Sine Transform), KLT (Karhunen-Loeve Transform), GBT (Graph-Based Transform), or CNT (Conditionally Non-linear Transform). Can include. Here, GBT refers to the transformation obtained from this graph when the relationship information between pixels is expressed in a graph. CNT refers to a transformation obtained based on generating a prediction signal using all previously reconstructed pixels. In addition, the conversion process may be applied to a pixel block having the same size of a square, or may be applied to a block having a variable size other than a square.

The quantization unit 133 quantizes the transform coefficients and transmits it to the entropy encoding unit 140, and the entropy encoding unit 140 encodes the quantized signal (information on quantized transform coefficients) and outputs it as a bitstream. have. Information about the quantized transform coefficients may be called residual information. The quantization unit 133 may rearrange the quantized transform coefficients in a block form into a one-dimensional vector form based on a coefficient scan order, and the quantized transform coefficients in the form of the one-dimensional vector It is also possible to generate information about transform coefficients. The entropy encoding unit 140 may perform various encoding methods such as exponential Golomb, context-adaptive variable length coding (CAVLC), context-adaptive binary arithmetic coding (CABAC), and the like. The entropy encoding unit 140 may encode information necessary for video/image restoration (eg, values of syntax elements) together or separately in addition to the quantized transform coefficients. The encoded information (eg, encoded video/video information) may be transmitted or stored in a bitstream form in units of network abstraction layer (NAL) units. The video/video information may further include information on various parameter sets, such as an adaptation parameter set (APS), a picture parameter set (PPS), a sequence parameter set (SPS), or a video parameter set (VPS). In addition, the video/video information may further include general constraint information. In this document, information and/or syntax elements transmitted/signaled from the encoding device to the decoding device may be included in the video/video information. The video/video information may be encoded through the above-described encoding procedure and included in the bitstream. The bitstream may be transmitted through a network or may be stored in a digital storage medium. Here, the network may include a broadcasting network and/or a communication network, and the digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, and SSD. For the signal output from the entropy encoding unit 140, a transmission unit (not shown) for transmitting and/or a storage unit (not shown) for storing may be configured as an internal/external element of the encoding apparatus 100, or the transmission unit It may be included in the entropy encoding unit 140.

The quantized transform coefficients output from the quantization unit 133 may be used to generate a prediction signal. For example, a residual signal (residual block or residual samples) may be restored by applying inverse quantization and inverse transform to the quantized transform coefficients through the inverse quantization unit 134 and the inverse transform unit 135. The addition unit 155 adds the reconstructed residual signal to the prediction signal output from the inter prediction unit 121 or the intra prediction unit 122 to obtain a reconstructed signal (restored picture, reconstructed block, reconstructed sample array). Can be created. When there is no residual for a block to be processed, such as when the skip mode is applied, the predicted block may be used as a reconstructed block. The addition unit 150 may be referred to as a restoration unit or a restoration block generation unit. The generated reconstructed signal may be used for intra prediction of the next processing target block in the current picture, and may be used for inter prediction of the next picture through filtering as described later.

Meanwhile, luma mapping with chroma scaling (LMCS) may be applied in the process of encoding and/or reconstructing a picture.

The filtering unit 160 may improve subjective/objective image quality by applying filtering to the reconstructed signal. For example, the filtering unit 160 may apply various filtering methods to the reconstructed picture to generate a modified reconstructed picture, and the modified reconstructed picture may be converted to the memory 170, specifically, the DPB of the memory 170. Can be saved on. The various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, and the like. The filtering unit 160 may generate a variety of filtering information and transmit it to the entropy encoding unit 140 as described later in the description of each filtering method. The filtering information may be encoded by the entropy encoding unit 140 and output in the form of a bitstream.

The modified reconstructed picture transmitted to the memory 170 may be used as a reference picture in the inter prediction unit 121. When inter prediction is applied through this, the encoding device may avoid prediction mismatch between the encoding device 100 and the decoding device, and may improve encoding efficiency.

The memory 170 DPB may store the modified reconstructed picture to be used as a reference picture in the inter prediction unit 121. The memory 170 may store motion information of a block from which motion information in a current picture is derived (or encoded) and/or motion information of blocks in a picture that have already been reconstructed. The stored motion information may be transmitted to the inter prediction unit 121 in order to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block. The memory 170 may store reconstructed samples of reconstructed blocks in the current picture, and may be transmitted to the intra prediction unit 122.

2 is a diagram schematically illustrating a configuration of a video/video decoding apparatus applicable to embodiments of the present document.

Referring to FIG. 2, the decoding apparatus 200 includes an entropy decoder 210, a residual processor 220, a predictor 230, an adder 240, and a filtering unit. It may be configured to include (filter, 250) and memory (memory) 260. The prediction unit 230 may include an inter prediction unit 231 and an intra prediction unit 232. The residual processing unit 220 may include a dequantizer 221 and an inverse transformer 221. The entropy decoding unit 210, the residual processing unit 220, the prediction unit 230, the addition unit 240, and the filtering unit 250 described above are one hardware component (for example, a decoder chipset or a processor). ) Can be configured. In addition, the memory 260 may include a decoded picture buffer (DPB), and may be configured by a digital storage medium. The hardware component may further include the memory 260 as an internal/external component.

When a bitstream including video/image information is input, the decoding apparatus 200 may reconstruct an image in response to a process in which the video/image information is processed by the encoding device of FIG. 1. For example, the decoding apparatus 200 may derive units/blocks based on block division related information obtained from the bitstream. The decoding device 200 may perform decoding using a processing unit applied by the encoding device. Thus, the processing unit of decoding may be, for example, a coding unit, and the coding unit may be divided from a coding tree unit or a maximum coding unit along a quad tree structure, a binary tree structure and/or a ternary tree structure. One or more transform units may be derived from the coding unit. In addition, the reconstructed image signal decoded and output through the decoding device 200 may be reproduced through the playback device.

The decoding apparatus 200 may receive a signal output from the encoding apparatus of FIG. 1 in the form of a bitstream, and the received signal may be decoded through the entropy decoding unit 210. For example, the entropy decoding unit 210 may parse the bitstream to derive information (eg, video/video information) necessary for image restoration (or picture restoration). The video/video information may further include information on various parameter sets, such as an adaptation parameter set (APS), a picture parameter set (PPS), a sequence parameter set (SPS), or a video parameter set (VPS). In addition, the video/video information may further include general constraint information. The decoding apparatus may further decode the picture based on the information on the parameter set and/or the general restriction information. Signaled/received information and/or syntax elements described later in this document may be decoded through the decoding procedure and obtained from the bitstream. For example, the entropy decoding unit 210 decodes information in the bitstream based on a coding method such as exponential Golomb coding, CAVLC, or CABAC, and a value of a syntax element required for image reconstruction, and a quantized value of a transform coefficient related to a residual. Can be printed. In more detail, the CABAC entropy decoding method receives a bin corresponding to each syntax element in a bitstream, and includes information about the syntax element to be decoded and information on the decoding information of the block to be decoded and the neighboring block or symbol/bin information decoded in a previous step. A context model is determined using the context model, and a symbol corresponding to the value of each syntax element can be generated by performing arithmetic decoding of the bin by predicting the probability of occurrence of a bin according to the determined context model. have. In this case, the CABAC entropy decoding method may update the context model using information of the decoded symbol/bin for the context model of the next symbol/bin after the context model is determined. Among the information decoded by the entropy decoding unit 210, information about prediction is provided to the prediction unit (inter prediction unit 232 and intra prediction unit 231), and the register on which entropy decoding is performed by the entropy decoding unit 210 Dual values, that is, quantized transform coefficients and related parameter information may be input to the residual processing unit 220. The residual processing unit 220 may derive a residual signal (residual block, residual samples, residual sample array). In addition, information about filtering among information decoded by the entropy decoding unit 210 may be provided to the filtering unit 250. Meanwhile, a receiving unit (not shown) for receiving a signal output from the encoding device may be further configured as an inner/outer element of the decoding device 200, or the receiving unit may be a component of the entropy decoding unit 210. Meanwhile, the decoding apparatus according to this document may be referred to as a video/video/picture decoding apparatus, and the decoding apparatus can be divided into an information decoder (video/video/picture information decoder) and a sample decoder (video/video/picture sample decoder). May be. The information decoder may include the entropy decoding unit 210, and the sample decoder includes the inverse quantization unit 221, an inverse transform unit 222, an addition unit 240, a filtering unit 250, and a memory 260. ), an inter prediction unit 232 and an intra prediction unit 231 may be included.

The inverse quantization unit 221 may inverse quantize the quantized transform coefficients and output transform coefficients. The inverse quantization unit 221 may rearrange the quantized transform coefficients into a two-dimensional block shape. In this case, the rearrangement may be performed based on the coefficient scan order performed by the encoding device. The inverse quantization unit 221 may perform inverse quantization on quantized transform coefficients using a quantization parameter (eg, quantization step size information) and obtain transform coefficients.

The inverse transform unit 222 obtains a residual signal (residual block, residual sample array) by inverse transforming the transform coefficients.

The prediction unit may perform prediction on the current block and generate a predicted block including prediction samples for the current block. The prediction unit may determine whether intra prediction or inter prediction is applied to the current block based on the prediction information output from the entropy decoding unit 210, and may determine a specific intra/inter prediction mode.

The prediction unit 220 may generate a prediction signal based on various prediction methods to be described later. For example, the prediction unit may apply intra prediction or inter prediction to predict one block, as well as simultaneously apply intra prediction and inter prediction. This can be called combined inter and intra prediction (CIIP). In addition, the prediction unit may be based on an intra block copy (IBC) prediction mode or a palette mode for prediction of a block. The IBC prediction mode or the palette mode may be used for content image/video coding such as a game, such as, for example, screen content coding (SCC). IBC basically performs prediction in the current picture, but can be performed similarly to inter prediction in that it derives a reference block in the current picture. That is, the IBC may use at least one of the inter prediction techniques described in this document. The palette mode can be viewed as an example of intra coding or intra prediction. When the palette mode is applied, information on a palette table and a palette index may be included in the video/video information and signaled.

The intra prediction unit 231 may predict the current block by referring to samples in the current picture. The referenced samples may be located in the vicinity of the current block or may be located away from each other according to the prediction mode. In intra prediction, prediction modes may include a plurality of non-directional modes and a plurality of directional modes. The intra prediction unit 231 may determine a prediction mode applied to the current block by using the prediction mode applied to the neighboring block.

The inter prediction unit 232 may derive a predicted block for the current block based on a reference block (reference sample array) specified by a motion vector on the reference picture. In this case, in order to reduce the amount of motion information transmitted in the inter prediction mode, motion information may be predicted in units of blocks, subblocks, or samples based on a correlation between motion information between a neighboring block and a current block. The motion information may include a motion vector and a reference picture index. The motion information may further include inter prediction direction (L0 prediction, L1 prediction, Bi prediction, etc.) information. In the case of inter prediction, the neighboring block may include a spatial neighboring block existing in the current picture and a temporal neighboring block existing in the reference picture. For example, the inter prediction unit 232 may construct a motion information candidate list based on neighboring blocks, and derive a motion vector and/or a reference picture index of the current block based on the received candidate selection information. Inter prediction may be performed based on various prediction modes, and the information on the prediction may include information indicating a mode of inter prediction for the current block.

The addition unit 240 is reconstructed by adding the obtained residual signal to the prediction signal (predicted block, prediction sample array) output from the prediction unit (including the inter prediction unit 232 and/or intra prediction unit 231). A signal (restored picture, reconstructed block, reconstructed sample array) can be generated. When there is no residual for a block to be processed, such as when the skip mode is applied, the predicted block may be used as a reconstructed block.

The addition unit 240 may be referred to as a restoration unit or a restoration block generation unit. The generated reconstructed signal may be used for intra prediction of the next processing target block in the current picture, may be output through filtering as described later, or may be used for inter prediction of the next picture.

Meanwhile, luma mapping with chroma scaling (LMCS) may be applied in the picture decoding process.

The filtering unit 250 may improve subjective/objective image quality by applying filtering to the reconstructed signal. For example, the filtering unit 250 may generate a modified reconstructed picture by applying various filtering methods to the reconstructed picture, and the modified reconstructed picture may be converted to the memory 260, specifically, the DPB of the memory 260. Can be transferred to. The various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, and the like.

The (modified) reconstructed picture stored in the DPB of the memory 260 may be used as a reference picture in the inter prediction unit 232. The memory 260 may store motion information of a block from which motion information in a current picture is derived (or decoded) and/or motion information of blocks in a picture that have already been reconstructed. The stored motion information may be transmitted to the inter prediction unit 232 in order to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block. The memory 260 may store reconstructed samples of reconstructed blocks in the current picture, and may be transmitted to the intra prediction unit 231.

In this document, the embodiments described in the filtering unit 160, the inter prediction unit 121, and the intra prediction unit 122 of the encoding apparatus 100 are respectively a filtering unit 250 and an inter prediction unit of the decoding apparatus 200. The same or corresponding to the unit 232 and the intra prediction unit 231 may be applied.

As described above, prediction is performed to increase compression efficiency in performing video coding. Through this, a predicted block including prediction samples for a current block, which is a block to be coded, may be generated. Here, the predicted block includes prediction samples in the spatial domain (or pixel domain). The predicted block is derived equally from the encoding device and the decoding device, and the encoding device signals information about the residual between the original block and the predicted block (residual information), not the original sample value of the original block, to the decoding device. Image coding efficiency can be improved. The decoding apparatus may derive a residual block including residual samples based on the residual information, and generate a reconstructed block including reconstructed samples by adding the residual block and the predicted block, and reconstruct including the reconstructed blocks. You can create pictures.

The residual information may be generated through transformation and quantization procedures. For example, the encoding apparatus derives a residual block between an original block and a predicted block, performs a transformation procedure on residual samples (residual sample array) included in the residual block to derive transform coefficients, and transforms By performing a quantization procedure on the coefficients to derive quantized transform coefficients, related residual information may be signaled to a decoding apparatus (via a bitstream). Here, the residual information may include information such as value information of quantized transform coefficients, position information, a transform technique, a transform kernel, and a quantization parameter. The decoding apparatus may perform an inverse quantization/inverse transform procedure based on the residual information and derive residual samples (or residual blocks). The decoding apparatus may generate a reconstructed picture based on the predicted block and the residual block. The encoding apparatus may also inverse quantize/inverse transform quantized transform coefficients for reference for inter prediction of a picture to derive a residual block, and generate a reconstructed picture based on the inverse quantization/inverse transformation of the quantized transform coefficients.

3 schematically shows a multi-transformation technique according to this document.

Referring to FIG. 3, the transform unit may correspond to the transform unit in the encoding apparatus of FIG. 1 described above, and the inverse transform unit may correspond to the inverse transform unit in the encoding apparatus of FIG. 1 or the inverse transform unit in the decoding apparatus of FIG. 2. .

The transform unit may derive (first-order) transform coefficients by performing a first-order transform based on residual samples (residual sample array) in the residual block (S310). This primary transform may be referred to as a core transform. Here, the first-order transform may be based on multiple transform selection (MTS), and when multiple transforms are applied as the first-order transform, it may be referred to as a multiple core transform.

The multiple core transformation may represent a method of additionally using Discrete Cosine Transform (DST) type 2, Discrete Sine Transform (DST) type 7, DCT type 8, and/or DST type 1. That is, the multi-core transform is based on a plurality of transform kernels selected from among the DCT type 2, the DST type 7, the DCT type 8, and the DST type 1, based on the residual signal (or residual block) in the spatial domain in the frequency domain. It may represent a transform method of transforming into transform coefficients (or first-order transform coefficients) of. Here, the first-order transform coefficients may be referred to as temporary transform coefficients from the viewpoint of the transform unit.

In other words, when a conventional transformation method is applied, transformation coefficients can be generated by applying a transformation from a spatial domain to a frequency domain for a residual signal (or a residual block) based on DCT type 2. In contrast, when the multi-core transformation is applied, the frequency domain in the spatial domain for a residual signal (or a residual block) based on DCT type 2, DST type 7, DCT type 8, and/or DST type 1, etc. Transform to may be applied to generate transform coefficients (or first-order transform coefficients). Here, DCT type 2, DST type 7, DCT type 8, and DST type 1 may be referred to as a transform type, a transform kernel, or a transform core. These DCT/DST conversion types may be defined based on basis functions.

When the multi-core transformation is performed, a vertical transformation kernel and a horizontal transformation kernel for a target block may be selected among the transformation kernels, and a vertical transformation for the target block is performed based on the vertical transformation kernel, and the Horizontal transformation may be performed on the target block based on the horizontal transformation kernel. Here, the horizontal transformation may represent transformation of horizontal components of the target block, and the vertical transformation may represent transformation of vertical components of the target block. The vertical transform kernel/horizontal transform kernel may be adaptively determined based on a prediction mode and/or a transform index of a target block (CU or subblock) including a residual block.

In addition, according to an example, in the case of performing a first-order transformation by applying MTS, specific basis functions are set to a predetermined value, and in the case of vertical transformation or horizontal transformation, which basis functions are applied are combined to determine the transformation kernel. Mapping relationship can be set. For example, if the horizontal direction conversion kernel is represented by trTypeHor and the vertical direction conversion kernel is represented by trTypeVer, the value of trTypeHor or trTypeVer is set to DCT2, the value of trTypeHor or trTypeVer is set to DST7, and the value of trTypeHor or trTypeVer is 2 May be set to DCT8.

In this case, MTS index information may be encoded and signaled to a decoding device to indicate any one of a plurality of transform kernel sets. For example, if the MTS index is 0, it indicates that both the trTypeHor and trTypeVer values are 0, if the MTS index is 1, it indicates that both the trTypeHor and trTypeVer values are 1, and if the MTS index is 2, the trTypeHor value is 2 and the trTypeVer value Is 1, if the MTS index is 3, the trTypeHor value is 1 and the trTypeVer value is 2, and if the MTS index is 4, it may indicate that both the trTypeHor and trTypeVer values are 2.

According to an example, a conversion kernel set according to MTS index information is shown in a table as follows.

The transform unit may derive modified (second-order) transform coefficients by performing a second-order transform based on the (first-order) transform coefficients (S320). The first-order transform is a transform from a spatial domain to a frequency domain, and the second-order transform refers to transforming into a more compressive expression using a correlation existing between (first-order) transform coefficients. The second-order transform may include a non-separable transform. In this case, the second transform may be referred to as a non-separable secondary transform (NSST) or a mode-dependent non-separable secondary transform (MDNSST). The non-separated quadratic transform is a second-order transform of the (first-order) transform coefficients derived through the first-order transform based on a non-separable transform matrix, and then modified transform coefficients for a residual signal. It may represent a transform that produces (or quadratic transform coefficients). Here, based on the non-separated transform matrix, a transform may be applied at once without separating vertical transform and horizontal transform (or independently applying horizontal and vertical transform) to the (first-order) transform coefficients. In other words, the non-separated quadratic transform is not separately applied in the vertical direction and the horizontal direction for the (first-order) transform coefficients, and, for example, the two-dimensional signals (transform coefficients) are in a specific direction (e.g., row priority). After rearranging into a one-dimensional signal through (row-first) direction or column-first direction), modified transform coefficients (or quadratic transform coefficients) are generated based on the non-separated transform matrix. The conversion method can be indicated. For example, the row priority order is to arrange the first row, the second row, ..., the Nth row for the MxN block in a row, and the column priority order is the first column, the second column for the MxN block. It is arranged in a row in the order of the column, ..., the Mth column. The non-separated quadratic transform may be applied to a top-left region of a block (hereinafter, referred to as a transform coefficient block) composed of (first-order) transform coefficients. For example, when both the width W and the height H of the transform coefficient block are equal to or greater than 8, an 8×8 non-separated quadratic transform may be applied to the upper left 8×8 area of the transform coefficient block. In addition, when both the width (W) and the height (H) of the transform coefficient block are 4 or more, and the width (W) or the height (H) of the transform coefficient block is less than 8, 4×4 non-separated secondary A transform can be applied to the upper left min(8,W)×min(8,H) area of the transform coefficient block. However, the embodiment is not limited thereto, and for example, even if only the condition that the width (W) or the height (H) of the transform coefficient block is 4 or more is satisfied, the 4×4 non-separated quadratic transform is the upper left corner of the transform coefficient block. It can also be applied to the region min(8,W)×min(8,H).

Specifically, for example, when a 4×4 input block is used, non-separated quadratic transformation may be performed as follows.

The 4×4 input block X can be represented as follows.

When X is expressed in vector form, a vector

Can be represented as follows.

As in Equation 2, the vector

Rearranges the two-dimensional block of X in Equation 1 into a one-dimensional vector according to the row-first order.

In this case, the second-order non-separated transform can be calculated as follows.

here,

Denotes a transform coefficient vector, and T denotes a 16x16 (non-separated) transform matrix.

A 16×1 transform coefficient vector through Equation 3 above

Can be derived, and the above

Can be re-organized into 4×4 blocks through a scan order (horizontal, vertical, diagonal, etc.). However, the above-described calculation is an example, and in order to reduce the computational complexity of the non-separated quadratic transform, HyGT (Hypercube-Givens Transform) or the like may be used for the calculation of the non-separated quadratic transform.

Meanwhile, for the non-separated secondary transformation, a transformation kernel (or transformation core, transformation type) may be selected in a mode dependent manner. Here, the mode may include an intra prediction mode and/or an inter prediction mode.

As described above, the non-separated quadratic transform may be performed based on an 8×8 transform or a 4×4 transform determined based on the width (W) and height (H) of the transform coefficient block. The 8x8 transform refers to a transform that can be applied to an 8x8 area included in a corresponding transform coefficient block when both W and H are equal to or greater than 8, and the 8x8 area may be an upper left 8x8 area inside the corresponding transform coefficient block. Similarly, the 4x4 transform refers to a transform that can be applied to a 4x4 area included in the corresponding transform coefficient block when both W and H are equal to or greater than 4, and the 4x4 area may be the upper left 4x4 area inside the corresponding transform coefficient block. . For example, an 8x8 transform kernel matrix may be a 64x64/16x64 matrix, and a 4x4 transform kernel matrix may be a 16x16/8x16 matrix.

At this time, for mode-based conversion kernel selection, two non-separated quadratic transform kernels may be configured per transform set for non-separated quadratic transform for both 8×8 transform and 4×4 transform, and the transform set is There can be four. That is, four transform sets may be configured for an 8×8 transform, and four transform sets may be configured for a 4×4 transform. In this case, four transform sets for an 8×8 transform may contain two 8×8 transform kernels, and in this case, four transform sets for a 4×4 transform include two 4×4 transform kernels each. Can be included.

However, the size of the transform, that is, the size of the region to which the transform is applied, may be a size other than 8×8 or 4×4 as an example, the number of sets is n, and the number of transform kernels in each set is k It could be a dog.

The transform set may be referred to as an NSST set or an LFNST set. Selection of a specific set among the transform sets may be performed, for example, based on an intra prediction mode of a current block (CU or subblock). LFNST (Low-Frequency Non-Separable Transform) may be an example of a reduced non-separable transform to be described later, and represents a non-separated transform for a low frequency component.

For reference, for example, the intra prediction mode is two non-directinoal or non-angular intra prediction modes and 65 directional or angular intra prediction modes. Can include. The non-directional intra prediction modes may include a planar intra prediction mode 0 and a DC intra prediction mode 1, and the directional intra prediction modes may include 65 intra prediction modes 2 to 66. . However, this is an example, and this document may be applied even when the number of intra prediction modes is different. Meanwhile, in some cases, the intra prediction mode 67 may be further used, and the intra prediction mode 67 may represent a linear model (LM) mode.

4 exemplarily shows intra-directional modes of 65 prediction directions.

Referring to FIG. 4, an intra prediction mode having horizontal directionality and an intra prediction mode having vertical directionality can be distinguished based on an intra prediction mode 34 having a downward-right diagonal prediction direction. H and V in FIG. 4 denote horizontal and vertical directions, respectively, and numbers from -32 to 32 denote displacements of 1/32 units on a sample grid position. This may represent an offset to the mode index value. Intra prediction modes 2 to 33 have horizontal directionality, and intra prediction modes 34 to 66 have vertical directionality. On the other hand, the 34th intra prediction mode can be considered to be neither horizontal nor vertical, strictly speaking, but it can be classified as belonging to horizontal directionality from the viewpoint of determining a transform set of a quadratic transform. This is because the input data is transposed and used for the vertical direction mode symmetrical around the 34th intra prediction mode, and the input data alignment method for the horizontal direction mode is used for the 34th intra prediction mode. Transposing the input data means that rows become columns and columns become rows for the 2D block data MxN to form NxM data. Intra prediction mode 18 and intra prediction mode 50 represent horizontal intra prediction mode and vertical intra prediction mode, respectively, and intra prediction mode 2 has a left reference pixel and is up-right direction. Because it predicts as, it may be referred to as an upward-right diagonal intra prediction mode, and in the same context, the 34th intra prediction mode may be referred to as a downward-right diagonal intra prediction mode, and the 66th intra prediction mode may be referred to as a left-downward diagonal intra prediction mode.

According to an example, mapping of four transform sets according to an intra prediction mode may be represented, for example, as shown in the following table.

As shown in Table 2, one of four transform sets, that is, lfnstTrSetIdx, may be mapped to any one of 0 to 3, that is, four according to the intra prediction mode.

Meanwhile, when it is determined that a specific set is used for non-separated transformation, one of k transformation kernels in the specific set may be selected through a non-separated quadratic transformation index. The encoding device may derive a non-separated quadratic transformation index indicating a specific transformation kernel based on a rate-distortion (RD) check, and may signal the non-separated quadratic transformation index to the decoding device. The decoding apparatus may select one of k transform kernels in a specific set based on the non-separated quadratic transform index. For example, the lfnst index value 0 may refer to the first non-separated quadratic transformation kernel, the lfnst index value 1 may refer to the second non-separated quadratic transformation kernel, and the lfnst index value 2 may refer to the third non-separated quadratic transformation kernel. Can point to. Alternatively, the lfnst index value 0 may indicate that the first non-separated quadratic transformation is not applied to the target block, and the lfnst index values 1 to 3 may indicate the three transformation kernels.

The transform unit may perform the non-separated quadratic transform based on the selected transform kernels and obtain modified (quaternary) transform coefficients. The modified transform coefficients may be derived as quantized transform coefficients through a quantization unit as described above, and may be encoded and transmitted to a signaling and inverse quantization/inverse transform unit in an encoding apparatus and signaling to a decoding apparatus.

Meanwhile, when the second-order transform is omitted as described above, the (first-order) transform coefficients that are the output of the first-order (separate) transform may be derived as quantized transform coefficients through the quantization unit as described above, and are encoded. It may be transmitted to a decoding device to an inverse quantization/inverse transform unit in a signaling and encoding device.

The inverse transform unit may perform a series of procedures in the reverse order of the procedure performed by the above-described transform unit. The inverse transform unit receives (inverse quantized) transform coefficients, performs a second-order (inverse) transform to derive (first-order) transform coefficients (S350), and first-order (inverse) with respect to the (first-order) transform coefficients. A residual block (residual samples) may be obtained by performing transformation (S360). Here, the first-order transform coefficients may be referred to as modified transform coefficients from the standpoint of the inverse transform unit. As described above, the encoding apparatus and the decoding apparatus may generate a reconstructed block based on the residual block and the predicted block, and generate a reconstructed picture based on the residual block and the predicted block.

Meanwhile, the decoding apparatus may further include a second-order inverse transform determining unit (or an element determining whether to apply a second-order inverse transform) and a second-order inverse transform determining unit (or a second-order inverse transform determining element). Whether to apply the second-order inverse transform may determine whether to apply the second-order inverse transform. For example, the second-order inverse transform may be NSST, RST, or LFNST, and the application of the second-order inverse transform may determine whether to apply the second-order inverse transform based on the second-order transform flag parsed from the bitstream. As another example, the determining unit whether to apply the second-order inverse transform may determine whether to apply the second-order inverse transform based on a transform coefficient of the residual block.

The second-order inverse transform determiner may determine a second-order inverse transform. In this case, the second-order inverse transform determiner may determine a second-order inverse transform applied to the current block based on the LFNST (NSST or RST) transform set specified according to the intra prediction mode. In addition, as an embodiment, the method for determining the second-order transformation may be determined depending on the method for determining the first-order transformation. Various combinations of the first-order transform and the second-order transform may be determined according to the intra prediction mode. Also, as an example, the inverse quadratic transform determiner may determine a region to which the inverse quadratic transform is applied based on the size of the current block.

Meanwhile, when the second-order (inverse) transform is omitted as described above, a residual block (residual samples) may be obtained by receiving the (inverse quantized) transform coefficients and performing the first-order (separation) inverse transform. . As described above, the encoding apparatus and the decoding apparatus may generate a reconstructed block based on the residual block and the predicted block, and generate a reconstructed picture based on the residual block and the predicted block.

Meanwhile, in this document, a reduced secondary transform (RST) with a reduced size of a transform matrix (kernel) can be applied from the concept of NSST in order to reduce the amount of computation and memory required for the non-separated quadratic transform.

Meanwhile, the transform kernel, the transform matrix, and the coefficients constituting the transform kernel matrix described in this document, that is, the kernel coefficient or the matrix coefficient may be represented by 8 bits. This may be one condition to be implemented in the decoding device and the encoding device, and it is possible to reduce the amount of memory required for storing the conversion kernel while accompanied by a performance degradation that can be reasonably accommodated compared to the existing 9-bit or 10-bit. . In addition, by expressing the kernel matrix in 8 bits, a small multiplier can be used, and it can be more suitable for a single instruction multiple data (SIMD) instruction used for optimal software implementation.

In this specification, RST may mean a transformation performed on residual samples for a target block based on a transform matrix whose size is reduced according to a simplification factor. In the case of performing the simplified transformation, the amount of computation required for transformation may be reduced due to a reduction in the size of the transformation matrix. That is, the RST can be used to solve an issue of computational complexity that occurs during transformation or non-separation transformation of a large block.

RST may be referred to in various terms such as reduced transform, reduced transform, reduced transform, reduced secondary transform, reduction transform, simplified transform, simple transform, and the like, and the name to which the RST may be referred to is not limited to the listed examples. Alternatively, since RST is mainly performed in a low frequency region including a non-zero coefficient in a transform block, it may be referred to as a low-frequency non-separable transform (LFNST). The conversion index may be referred to as an LFNST index.

Meanwhile, when the second-order inverse transform is based on RST, the inverse transform unit 135 of the encoding device 100 and the inverse transform unit 222 of the decoding device 200 are transformed based on the inverse RST of the transform coefficients. An inverse RST unit for deriving coefficients, and an inverse linear transform unit for deriving residual samples for the target block based on an inverse linear transformation for the modified transform coefficients. The inverse first-order transform means the inverse transform of the first-order transform applied to the residual. In this document, deriving a transform coefficient based on a transform may mean deriving a transform coefficient by applying a corresponding transform.

In the present specification, “target block” may mean a current block, a residual block, or a transform block on which coding is performed.

In the RST according to an embodiment, a reduced transformation matrix may be determined by mapping an N dimensional vector to an R dimensional vector located in a different space, where R is less than N. N may mean the square of the length of one side of the block to which the transform is applied or the total number of transform coefficients corresponding to the block to which the transform is applied, and the simplification factor may mean an R/N value. The simplification factor may be referred to in various terms such as a reduced factor, a reduction factor, a reduced factor, a reduction factor, a simplified factor, and a simple factor. Meanwhile, R may be referred to as a reduced coefficient, but in some cases, the simplified factor may mean R. In addition, in some cases, the simplification factor may mean an N/R value.

In an embodiment, the simplification factor or the simplification factor may be signaled through a bitstream, but the embodiment is not limited thereto. For example, a predefined value for the simplification factor or simplification coefficient may be stored in each encoding device 100 and the decoding device 200, and in this case, the simplification factor or the simplification factor may not be signaled separately.

The size of the simplified transform matrix according to an embodiment is RxN, which is smaller than the size NxN of a conventional transform matrix, and may be defined as in Equation 4 below.

The matrix T in the Reduced Transform block shown in FIG. _{5A may mean the matrix T RxN of Equation 4.} As shown in FIG. 5A, when the simplified transform matrix T _RxN is multiplied with respect to residual samples for the target block, transform coefficients for the target block may be derived.

In one embodiment, when the size of the block to which the transformation is applied is 8x8 and R=16 (that is, R/N=16/64=1/4), the RST according to FIG. 5A is It can be expressed as a matrix operation such as Equation 5. In this case, memory and multiplication operations can be reduced to approximately 1/4 by a simplification factor.

In this document, a matrix operation can be understood as an operation to obtain a column vector by multiplying a matrix and a column vector by placing a matrix on the left side of the column vector.

In Equation 5, r ₁ to r ₆₄ may represent residual samples for a target block, and more specifically, may be transform coefficients generated by applying a first-order transform. As a result of the operation of Equation 5, the transform coefficients c _i for the target block may be derived, and _{the derivation process of c i} may be the same as in Equation 6.

As a result of the operation of Equation 6, transform coefficients c ₁ to c _R for the target block may be derived. That is, when R=16, transform coefficients c ₁ to c ₁₆ for the target block may be derived. If a transform matrix with a size of 64x64 (NxN) is multiplied by residual samples of a size of 64x1 (Nx1) because a regular transform rather than RST is applied, then 64 transform coefficients for the target block (N) Is derived, but since RST is applied, only 16 transform coefficients (R) are derived for the target block. Since the total number of transform coefficients for the target block is reduced from N to R, the amount of data transmitted by the encoding device 100 to the decoding device 200 decreases, so the transmission between the encoding device 100 and the decoding device 200 Efficiency can be increased.

From the viewpoint of the size of the transform matrix, the size of the normal transform matrix is 64x64 (NxN), but the size of the simplified transform matrix is reduced to 16x64 (RxN). Memory usage can be reduced by an R/N ratio. In addition, compared to the number of multiplication operations NxN when using a normal transform matrix, the use of the simplified transform matrix can reduce the number of multiplication operations by an R/N ratio (RxN).

In an embodiment, the transform unit 132 of the encoding apparatus 100 may derive transform coefficients for the target block by performing a first-order transform and an RST-based second-order transform on residual samples for the target block. These transform coefficients may be transmitted to the inverse transform unit of the decoding apparatus 200, and the inverse transform unit 222 of the decoding apparatus 200 derives the modified transform coefficients based on the inverse reduced secondary transform (RST) of the transform coefficients. Then, residual samples for the target block may be derived based on the inverse linear transform of the modified transform coefficients.

The size of the inverse RST matrix TNxR according to an embodiment is NxR, which is smaller than the size NxN of a conventional inverse transform matrix, and is in a transpose relationship with the simplified transform matrix TRxN shown in Equation 4.

Reduced Inv shown in Fig. 5 (b). The matrix T ^t in the Transform block may mean the inverse RST matrix T _RxN ^T (the superscript T means transpose). _{When the inverse RST matrix T RxN} ^T is multiplied with the transform coefficients for the target block as shown in FIG. 5B, modified transform coefficients for the target block or residual samples for the target block may be derived. . Station _RxN RST matrix T ^T may be expressed as ^(T _RxN) T _NxR.

More specifically, when inverse RST is applied as a second-order inverse transform, modified transform coefficients for the target block may be derived by multiplying _{transform coefficients for the target block by the inverse RST matrix T RxN} ^T. Meanwhile, an inverse RST may be applied as an inverse linear transformation, and in this case, residual samples for the target block may be derived when transform coefficients for the target block are multiplied by the inverse RST matrix TRxNT.

In one embodiment, when the size of the block to which the inverse transform is applied is 8x8 and R=16 (that is, when R/N=16/64=1/4), the RST according to (b) of FIG. 5 is It can be expressed as a matrix operation such as Equation 7 of.

In Equation 7, c ₁ to c ₁₆ may represent transform coefficients for the target block. _{As a result of the operation of Equation 7, r i} representing modified transform coefficients for the target block or residual samples for the target block may be derived, and _{a derivation process of r i} may be the same as in Equation 8.

_{As a result of the operation of Equation 8, r 1} to r _N representing the modified transform coefficients for the target block or residual samples for the target block may be derived. In terms of the size of the inverse transform matrix, the size of a typical inverse transform matrix is 64x64 (NxN), but the size of the simplified inverse transform matrix is reduced to 64x16 (NxR). Memory usage can be reduced by R/N ratio. In addition, compared to the number of multiplication operations NxN when using a normal inverse transform matrix, the use of the simplified inverse transform matrix can reduce the number of multiplication operations by an R/N ratio (NxR).

On the other hand, also for 8x8 RST, the transformation set configuration shown in Table 2 can be applied. That is, the 8x8 RST may be applied according to the transform set in Table 2. Since one transform set is composed of two or three transforms (kernels) according to an intra prediction mode, it may be configured to select one of a maximum of four transforms including a case where a quadratic transform is not applied. When the quadratic transformation is not applied, the transformation can be regarded as the identity matrix applied. Assuming that indexes of 0, 1, 2, and 3 are assigned to each of the four transformations (for example, index 0 can be assigned to an identity matrix, that is, when quadratic transformation is not applied), transformation index Alternatively, a transform to be applied may be designated by signaling a syntax element called an lfnst index for each transform coefficient block. That is, for an 8x8 upper left block through a transform index, 8x8 RST may be designated in the RST configuration, or 8x8 lfnst may be designated when LFNST is applied. 8x8 lfnst and 8x8 RST refer to transforms that can be applied to the 8x8 area included in the corresponding transform coefficient block when both W and H of the target block to be transformed are equal to or greater than 8, and the corresponding 8x8 area is the corresponding transform coefficient block. It may be an upper left 8x8 area inside. Similarly, 4x4 lfnst and 4x4 RST refer to transforms that can be applied to the 4x4 area included in the corresponding transform coefficient block when both W and H of the target block are equal to or greater than 4, and the 4x4 area is It may be the upper left 4x4 area.

Meanwhile, according to an embodiment of the present document, in the conversion of the encoding process, a maximum of 16 x 48 conversion kernels is selected by selecting only 48 data, not a 16 x 64 conversion kernel matrix, for 64 data constituting an 8 x 8 area. Matrix can be applied. Here, “maximum” means that the maximum value of m is 16 for an m x 48 transform kernel matrix capable of generating m coefficients. That is, when RST is performed by applying an m x 48 transform kernel matrix (m ≤ 16) to an 8 x 8 region, it is possible to generate m coefficients by receiving 48 data. When m is 16, 48 data are input and 16 coefficients are generated. That is, assuming that 48 pieces of data form a 48×1 vector, a 16×1 vector may be generated by sequentially multiplying a 16×48 matrix and a 48×1 vector. In this case, 48 x 1 vectors can be formed by appropriately arranging 48 pieces of data constituting an 8 x 8 area. For example, a 48x1 vector may be constructed based on 48 pieces of data constituting an area excluding a 4x4 area at the bottom right of an 8x8 area. At this time, when a matrix operation is performed by applying a maximum 16 x 48 transform kernel matrix, 16 modified transform coefficients are generated, and the 16 modified transform coefficients can be arranged in the upper left 4 x 4 area according to the scanning order, and the upper right The 4 x 4 area and the lower left 4 x 4 area may be filled with zeros.

The transposed matrix of the above-described transform kernel matrix may be used for the inverse transform of the decoding process. That is, when inverse RST or LFNST is performed as an inverse transformation process performed by the decoding apparatus, the input coefficient data to which the inverse RST is applied is composed of a 1-D vector according to a predetermined arrangement order, and the corresponding inverse RST matrix is added to the 1-D vector. The modified coefficient vectors obtained by multiplying from the left may be arranged in a 2D block according to a predetermined arrangement order.

In summary, in the conversion process, when RST or LFNST is applied to the 8x8 region, 48 transform coefficients in the upper left, upper right, and lower left regions of the 8x8 region excluding the lower right region of the 8x8 region, and the transformation of 16x48 Matrix operations with kernel matrices are performed. For matrix operation, 48 transform coefficients are input as a one-dimensional array. When such a matrix operation is performed, 16 modified transform coefficients are derived, and the modified transform coefficients may be arranged in the upper left area of the 8x8 area.

Conversely, in the inverse transform process, when inverse RST or LFNST is applied to the 8x8 region, 16 transform coefficients corresponding to the upper left of the 8x8 region among the transform coefficients of the 8x8 region are input in the form of a one-dimensional array according to the scanning order. A transform kernel matrix of 48 x 16 and a matrix can be computed. That is, the matrix operation in this case can be expressed as (48 x 16 matrix) * (16 x 1 transform coefficient vector) = (48 x 1 modified transform coefficient vector). Here, since the nx1 vector can be interpreted in the same meaning as the nx1 matrix, it may be expressed as an nx1 column vector. In addition, * means a matrix multiplication operation. When such a matrix operation is performed, 48 modified transform coefficients may be derived, and 48 modified transform coefficients may be arranged in the upper left, upper right, and lower left regions excluding the lower right region of the 8x8 region.

A detailed look at the above-described non-separated conversion and LFNST is as follows. The LFNST may include forward transformation by an encoding device and inverse transformation by a decoding device.

The encoding apparatus applies a primary (core) transform and then receives a result (or a part of the result) as an input, and applies a secondary transform.

In Equation 9, x and y are the inputs and outputs of the quadratic transformation, respectively, and G is a matrix representing the quadratic transformation, and transform basis vectors are composed of column vectors. In the case of reverse LFNST, when the dimension of the transformation matrix G is expressed as [number of rows x number of columns], in the case of forward LFNST, the dimension of ^{G T is obtained by taking the transforce of the matrix G.}

In the case of reverse LFNST, the dimensions of the matrix G are [48 x 16 ], [48 x 8 ], [16 x 16 ], and [16 x 8 ], and the [48 x 8] and [16 x 8] matrices are respectively This is a partial matrix obtained by sampling 8 transform basis vectors from the left of the [48 x 16] matrix and the [16 x 16] matrix.

On the other hand, in the case of forward LFNST, ^{the dimensions of the matrix G T} are [16 x 48 ], [8 x 48 ], [16 x 16 ], and [8 x 16 ], and [8 x 48] and [8 x 16] The matrix is a partial matrix obtained by sampling 8 transform basis vectors from the top of the [16 x 48] matrix and the [16 x 16] matrix, respectively.

Therefore, in the case of forward LFNST, a [48 x 1] vector or a [16 x 1] vector can be used as an input x, and a [16 x 1] vector or a [8 x 1] vector can be used as an output y. In video coding and decoding, since the output of the forward first-order transform is two-dimensional (2D) data, 2D data that is the output of the forward transform is properly arranged to form a [48 x 1] vector or a [16 x 1] vector as input x. We need to construct a dimensional vector.

6 is a diagram illustrating a sequence of arranging output data of a forward linear transformation into a one-dimensional vector, according to an example. Figures 6 (a) and (b) on the left shows a sequence for creating a [48 x 1] vector, and Figure 6 (a) and (b) on the right shows a [16 x 1] vector Indicate the order. In the case of LFNST, a one-dimensional vector x may be obtained by sequentially arranging 2D data in the order shown in FIGS. 6A and 6B.

The arrangement direction of the output data of the forward linear transformation may be determined according to the intra prediction mode of the current block. For example, if the intra prediction mode of the current block is in the horizontal direction based on the diagonal direction, the output data of the forward first order transformation may be arranged in the order of FIG. 6A, and the intra prediction mode of the current block is in the diagonal direction. In the vertical direction based on, the output data of the forward first-order transformation may be arranged in the order of (b) of FIG. 6.

According to an example, an arrangement order different from the ordering of FIGS. 6A and 6B may be applied, and the same as when the arrangement order of FIGS. 6A and 6B is applied. To derive the result (y vector), the column vectors of matrix G can be rearranged according to the corresponding arrangement order. That is, the column vectors of G can be rearranged so that each element constituting the x vector is always multiplied by the same transformed basis vector.

Since the output y derived through Equation 9 is a one-dimensional vector, if a configuration that processes the result of a forward quadratic transformation as an input, for example, a configuration that performs quantization or residual coding, requires two-dimensional data as input data. Then, the output y vector of Equation 9 must be properly arranged as 2D data.

In the case of LFNST, it may be placed in a 2D block according to a predetermined scan order. 7A shows that when the output y is a [16 x 1] vector, output values are arranged in a diagonal scan order at 16 positions of a 2D block. 7B shows that when the output y is a [8 x 1] vector, output values are arranged in the diagonal scan order at eight positions of the 2D block and the remaining eight positions are filled with zeros. X in (b) of FIG. 7 indicates that it is filled with zeros.

According to another example, since the order in which the output vector y is processed by a configuration that performs quantization or residual coding may be performed according to a preset order, the output vector y may not be arranged in the 2D block as shown in FIG. 7. . However, in the case of residual coding, data coding may be performed in units of 2D blocks (e.g., 4x4) such as CG (Coefficient Group), and in this case, data is arranged according to a specific order as in the diagonal scan order of FIG. Can be.

Meanwhile, the decoding apparatus may construct a 1D input vector y by arranging 2D data outputted through an inverse quantization process or the like for inverse transformation according to a preset scan order. The input vector y may be output as an input vector x by the following equation.

In the case of the reverse LFNST, the output vector x can be derived by multiplying the input vector y, which is a [16 x 1] vector or a [8 x 1] vector, by a G matrix. In the case of the reverse LFNST, the output vector x may be a [48 x 1] vector or a [16 x 1] vector.

The output vector x is arranged in a two-dimensional block according to the order shown in FIG. 6 to be arranged as two-dimensional data, and the two-dimensional data becomes input data (or part of the input data) of the reverse first-order transformation.

Accordingly, the reverse quadratic transform is generally opposite to the forward quadratic transform process, and in the case of the inverse transform, the reverse quadratic transform is applied first, and then the backward linear transform is applied, unlike in the forward direction.

In the reverse LFNST, one of eight [48 x 16] matrices and eight [16 x 16] matrices may be selected as the transform matrix G. Whether a [48 x 16] matrix or a [16 x 16] matrix is applied depends on the size and shape of the block.

In addition, eight matrices may be derived from four transform sets, as shown in Table 2 above, and each transform set may be composed of two matrices. Which of the four transform sets to use is determined according to the intra prediction mode, and more specifically, the transform set is determined based on the value of the extended intra prediction mode by considering the wide angle intra prediction mode (Wide Angle Intra Prediction, WAIP). do. Which of the two matrices constituting the selected transform set is selected is derived through index signaling. More specifically, as the transmitted index value, 0, 1, and 2 are possible, 0 indicates that LFNST is not applied, and 1 and 2 are two transforms constituting a transform set selected based on the intra prediction mode value. Any one of the matrices can be indicated.

Meanwhile, as described above, whether or not a transformation matrix among the [48 x 16] matrix and the [16 x 16] matrix is applied to the LFNST is determined by the size and shape of the block to be transformed.

8 is a diagram illustrating a block shape to which LFNST is applied. Figure 8 (a) shows 4 x 4 blocks, (b) shows 4 x 8 and 8 x 4 blocks, (c) shows 4 x N or N x 4 blocks in which N is 16 or more, and (d) shows 8 An x 8 block, (e) represents an M x N block in which M≥8, N≥8, and N>8 or M>8.

In FIG. 8, blocks with thick borders indicate areas to which LFNST is applied. For the blocks of FIGS. 8A and 8B, LFNST is applied to the top-left 4x4 area, and for the block of FIG. 8C, the two upper left 4x4 areas are continuously arranged. Each LFNST is applied. In (a), (b), and (c) of FIG. 8, since LFNST is applied in units of 4x4 regions, these LFNSTs will be referred to as “4x4 LFNST” below. Based on the matrix dimension for G, a [16 x 16] or [16 x 8] matrix may be applied.

More specifically, a [16 x 8] matrix is applied to the 4x4 block (4x4 TU or 4x4 CU) of FIG. 8(a), and [16 x 8] for the blocks in (b) and (c) of FIG. 8 16] The matrix is applied. This is to set the computational complexity for the worst case to 8 multiplications per sample.

In (d) and (e) of FIG. 8, LFNST is applied to the upper left 8x8 area, and this LFNST is hereinafter referred to as “8x8 LFNST”. As the corresponding transformation matrix, a [48 x 16] or [48 x 8] matrix may be applied. In the case of forward LFNST, a [48 x 1] vector (x vector in Equation 9) is input as input data, so all sample values in the upper left 8x8 area are not used as input values for forward LFNST. That is, as shown in the left order of FIG. 6(a) or the left order of FIG. 6(b), the 4x4 block at the bottom-right is left as it is, and samples belonging to the remaining 3 4x4 blocks are included. Based on [48 x 1] we can construct a vector.

A [48 x 8] matrix may be applied to an 8x8 block (8x8 TU or 8x8 CU) in FIG. 8(d), and a [48 x 16] matrix may be applied to an 8x8 block in FIG. 8(e). This is also to set the computational complexity for the worst case to 8 multiplications per sample.

If the corresponding forward LFNST (4x4 LFNST or 8x8 LFNST) is applied according to the block shape, 8 or 16 output data (y vector in Equation 9, [8 x 1] or [16 x 1] vector) are created. In the forward LFNST, the number of output data is equal to or less than the number of input data due to the characteristics of the matrix GT.

9 is a diagram illustrating an arrangement of output data of forward LFNST according to an example, and illustrates a block in which output data of forward LFNST is arranged according to a block shape.

The shaded area at the upper left of the block shown in FIG. 9 corresponds to the area where the output data of the forward direction LFNST is located, the location indicated by 0 indicates the samples filled with a value of 0, and the remaining area is changed by forward LFNST. Indicates the area that is not available. In an area that is not changed by LFNST, the output data of the forward primary transform remains unchanged.

As described above, since the dimension of the applied transformation matrix varies according to the block shape, the number of output data varies. As shown in FIG. 9, the output data of the forward LFNST may not fill the upper left 4x4 block. In the case of (a) and (d) of Fig. 9, a [16 x 8] matrix and a [48 x 8] matrix are applied to the block indicated by a thick line or a partial area inside the block, respectively, as the output of the forward LFNST [8 x 1 ] A vector is created. That is, only 8 output data may be filled as shown in FIGS. 9A and 9D according to the scan order shown in FIG. 7B, and 0 may be filled for the remaining 8 positions. In the case of the LFNST applied block of FIG. 8(d), two 4x4 blocks adjacent to the upper left 4x4 block and the lower left 4x4 blocks are also filled with 0 values as shown in FIG. 9(d).

As described above, the LFNST index is basically signaled to designate whether to apply LFNST and a transformation matrix to be applied. As shown in FIG. 9, when LFNST is applied, since the number of output data of the forward LFNST may be equal to or less than the number of input data, a region filled with a zero value occurs as follows.

1) As shown in Fig. 9(a), the positions after the 8th in the scan order in the upper left 4x4 block, that is, samples from the 9th to the 16th

2) As shown in (d) and (e) of Fig. 9, a [16 x 48] matrix or [8 x 48] matrix is applied to the two 4x4 blocks adjacent to the upper left 4x4 block, or the second and third in the scan order. 4x4 blocks

Therefore, if non-zero data exists by checking areas 1) and 2), it is certain that LFNST has not been applied, so that signaling of the corresponding LFNST index can be omitted.

According to an example, in the case of LFNST adopted in the VVC standard, for example, since signaling of the LFNST index is performed after residual coding, the encoding device uses non-zero data ( It is possible to know whether there is an effective coefficient). Accordingly, the encoding device may determine whether to perform signaling for the LFNST index based on whether non-zero data exists, and the decoding device may determine whether to parse the LFNST index. If non-zero data does not exist in the areas designated in 1) and 2) above, LFNST index signaling is performed.

Meanwhile, for the adopted LFNST, the following simplification methods may be applied.

(i) According to an example, the number of output data for forward LFNST may be limited to a maximum of 16.

In the case of (c) of FIG. 8, 4x4 LFNST may be applied to two 4x4 regions adjacent to the upper left, and at this time, up to 32 LFNST output data may be generated. If the number of output data for the forward LFNST is limited to a maximum of 16, 4x4 LFNST is applied to only one 4x4 area existing in the upper left corner even for a 4xN/Nx4 (N≥16) block (TU or CU). LFNST can be applied only once for all blocks. This can simplify the implementation of image coding.

(ii) According to an example, zero-out may be additionally applied to a region to which LFNST is not applied. In this document, zero-out may mean filling the values of all positions belonging to a specific area with a value of 0. That is, zero-out can be applied to a region that is not changed due to LFNST and maintains the result of the forward first-order transformation. As described above, since LFNST is divided into 4x4 LFNST and 8x8 LFNST, zero-out can be classified into two types ((ii)-(A) and (ii)-(B)) as follows.

(ii)-(A) When 4x4 LFNST is applied, a region to which 4x4 LFNST is not applied can be zeroed out. 10 is a diagram illustrating zero-out in a block to which 4x4 LFNST is applied according to an example.

As shown in FIG. 10, a block to which 4x4 LFNST is applied, that is, a region to which LFNST is not applied to the blocks of FIGS. 9A, 9B, and 9C may be all filled with zeros.

Meanwhile, FIG. 10D shows that, according to an example, when the maximum value of the number of output data of the forward LFNST is limited to 16, zero-out is performed for the remaining blocks to which 4x4 LFNST is not applied.

(ii)-(B) When 8x8 LFNST is applied, a region to which 8x8 LFNST is not applied may be zeroed out. 11 is a diagram illustrating zero-out in a block to which 8x8 LFNST is applied according to an example.

As shown in FIG. 11, the blocks to which the 8x8 LFNST is applied, that is, the areas to which the LFNST is not applied to the blocks of (d) and (e) of FIG. 9 may be all filled with 0s.

(iii) When the LFNST is applied due to the zero-out suggested in (ii) above, the area filled with zeros may vary. Therefore, whether non-zero data exists according to the zero-out proposed in (ii) above can be checked in a wider area than in the case of LFNST of FIG. 9.

For example, in the case of applying (ii)-(B), non-zero data is added to the area filled with 0 values in Fig. 9(d) and (e), and up to the area additionally filled with 0 in Fig. After checking whether there is presence or not, signaling for the LFNST index can be performed only when non-zero data does not exist.

Of course, even if the zero-out proposed in (ii) is applied, it is possible to check whether non-zero data exists as in the existing LFNST index signaling. That is, it is possible to check whether non-zero data exists in the block filled with zeros in FIG. 9 and apply LFNST index signaling. In this case, zero-out is performed only in the encoding device, and the decoding device does not assume that zero-out, that is, only checks whether non-zero data exists in the region explicitly marked as 0 in FIG. 9, and performs LFNST index parsing. can do.

Various embodiments to which a combination of the simplification methods for the LFNST ((i), (ii)-(A), (ii)-(B), and (iii)) can be derived. Of course, the combination of the simplification methods is not limited to the following embodiments, and any combination may be applied to the LFNST.

Example

-Limit the number of output data for forward LFNST to a maximum of 16 → (i)

-When 4x4 LFNST is applied, all areas to which 4x4 LFNST is not applied are zeroed out → (ii)-(A)

-When 8x8 LFNST is applied, all areas to which 8x8 LFNST is not applied are zeroed out → (ii)-(B)

-After checking whether non-zero data exists in the area filled with the existing 0 value and the area filled with 0 due to additional zero-out ((ii)-(A), (ii)-(B)) , LFNST indexing signaling only when non-zero data does not exist → (iii)

In the above embodiment, when LFNST is applied, the area in which non-zero output data can exist is limited to the inside of the upper left 4x4 area. In more detail, in the case of (a) of FIG. 10 and (a) of FIG. 11, the eighth position in the scan order is the last position in which non-zero data can exist, and In the case of (b) of FIG. 11, the 16th position in the scan order (that is, the position of the lower right corner of the upper left 4x4 block) is the last position in which non-zero data can exist.

Accordingly, when LFNST is applied, whether non-zero data exists at a position where the residual coding process is not allowed (at a position beyond the last position), and whether to signal the LFNST index may be determined.

In the case of the zero-out method proposed in (ii), since the number of data that is finally generated when both the first-order transformation and LFNST are applied is reduced, the amount of computation required when performing the entire transformation process can be reduced. That is, when LFNST is applied, zero-out is also applied to the forward primary transform output data existing in the region to which LFNST is not applied. There is no need to create it. Therefore, it is possible to save the amount of computation required to generate the corresponding data. The additional effects of the zero-out method proposed in (ii) are summarized as follows.

First, as described above, the amount of computation required to perform the entire conversion process is reduced.

In particular, when (ii)-(B) is applied, the amount of calculation for the worst case is reduced, and the conversion process can be lightened. In addition, in general, a large amount of computation is required to perform a large-sized first-order transformation. If (ii)-(B) is applied, the number of data derived as a result of performing forward LFNST can be reduced to 16 or less. , As the size of the entire block (TU or CU) increases, the effect of reducing the amount of conversion operation increases.

Second, the amount of computation required for the entire conversion process can be reduced, thereby reducing the power consumption required to perform the conversion.

Third, the latency involved in the conversion process is reduced.

A second-order transformation such as LFNST increases the total delay time involved in performing the transformation because the amount of calculation is added to the existing first-order transformation. In particular, in the case of intra prediction, since reconstructed data of neighboring blocks is used in the prediction process, an increase in delay time due to quadratic transformation during encoding leads to an increase in delay time until reconstruction, thereby increasing the overall delay time of intra prediction encoding. Can lead to

However, if the zero-out suggested in (ii) is applied, the delay time for performing the first-order conversion can be significantly reduced when applying LFNST, so the delay time for the entire conversion is maintained as it is or rather reduced, making the encoding device simpler. Can be implemented.

Meanwhile, in the conventional intra prediction, a block to be currently encoded is regarded as one coding unit, and coding is performed without splitting. However, ISP (Intra Sub-Paritions) coding refers to performing intra prediction coding by dividing a block to be currently coded in a horizontal direction or a vertical direction. In this case, a reconstructed block is generated by performing encoding/decoding in units of divided blocks, and the reconstructed block may be used as a reference block of the next divided block. According to an example, when coding an ISP, one coding block may be divided into two or four sub-blocks to be coded, and in the ISP, one sub-block is a reconstructed pixel value of an adjacent left or adjacent upper sub-block. Intra prediction is performed with reference. Hereinafter, “coding” used may be used as a concept including both coding performed by the encoding device and decoding performed by the decoding device.

The ISP divides a block predicted by luma intra into 2 or 4 sub-partitions in the vertical direction or the horizontal direction according to the size of the block. For example, the minimum block size that an ISP can apply is 4 x 8 or 8 x 4. If the block size is larger than 4 x 8 or 8 x 4, the block is divided into 4 sub-partitions.

When ISP is applied, sub-blocks are sequentially coded according to the division type, for example, horizontally or vertically, left to right, or top to bottom, and inverse transform and intra prediction for one sub-block are performed. After the reconstruction process is performed, coding for the next sub-block may be performed. For the leftmost or uppermost sub-block, a reconstructed pixel of an already coded coding block is referred to as in a conventional intra prediction method. In addition, when each side of the subsequent inner sub-block is not adjacent to the previous sub-block, the reconstructed pixels of the adjacent coding block that have already been coded as in the conventional intra prediction method are deduced to derive the reference pixels adjacent to the corresponding side. See.

In the ISP coding mode, all sub-blocks may be coded with the same intra prediction mode, and a flag indicating whether to use ISP coding and a flag indicating in which direction (horizontal or vertical) to be divided may be signaled. At this time, depending on the block shape, the number of sub-blocks can be adjusted to 2 or 4, and if the size (width x height) of one sub-block is less than 16, division into the sub-block is not allowed, or ISP coding It can be restricted not to apply itself.

Meanwhile, in the case of the ISP prediction mode, one coding unit is divided into 2 or 4 partition blocks, i.e., sub-blocks, and predicted, and the same intra prediction mode is applied to the divided 2 or 4 partition blocks. .

As described above, in the horizontal direction (when an MxN coding unit having a horizontal length and a vertical length of M and N, respectively, is divided in the horizontal direction, it is divided into Mx(N/2) blocks and divided into four. When it is divided, it is divided into Mx(N/4) blocks) and in the vertical direction (when the MxN coding unit is divided in the vertical direction, if it is divided into two, it is divided into (M/2)xN blocks and divided into four) (Divided into (M/4)xN blocks) are all possible. When partitioned in a horizontal direction, partition blocks are coded in an order from top to bottom, and when partitioned in a vertical direction, partition blocks are coded in an order from left to right. The currently coded partition block may be predicted by referring to reconstructed pixel values of the upper (left) partition block in the case of horizontal (vertical) division.

Transformation may be applied in units of partition blocks to the residual signal generated by the ISP prediction method. MTS (Multiple Transform Selection) technology based on the combination of DST-7/DCT-8 as well as the existing DCT-2 can be applied to the primary transform (core transform or primary transform) based on the forward direction. A forward Low Frequency Non-Separable Transform (LFNST) is applied to the generated transform coefficient to generate a final modified transform coefficient.

That is, LFNST may be applied to partition blocks divided by applying the ISP prediction mode, and the same intra prediction mode is applied to the divided partition blocks as described above. Accordingly, when selecting the LFNST set derived based on the intra prediction mode, the derived LFNST set can be applied to all partition blocks. That is, since the same intra prediction mode is applied to all partition blocks, the same LFNST set may be applied to all partition blocks.

Meanwhile, according to an example, LFNST may be applied only to a transform block having a horizontal and vertical length of 4 or more. Accordingly, when the horizontal or vertical length of the partition block divided according to the ISP prediction method is less than 4, LFNST is not applied and the LFNST index is not signaled. In addition, when LFNST is applied to each partition block, the corresponding partition block can be regarded as one transform block. Of course, if the ISP prediction method is not applied, LFNST may be applied to the coding block.

A detailed look at applying LFNST to each partition block is as follows.

According to an example, after applying forward LFNST to an individual partition block, only up to 16 coefficients (8 or 16) are left in the upper left 4x4 area according to the transform coefficient scanning order, and the remaining positions and areas are all 0 values. Filling zero out can be applied.

Alternatively, according to an example, when the length of one side of the partition block is 4, LFNST is applied only to the upper left 4x4 area, and when the length of all sides of the partition block, that is, the width and height is 8 or more, the upper left 8x8 area and the lower right 4x4 inside the area. LFNST can be applied to the remaining 48 coefficients excluding the region.

Alternatively, according to an example, in order to adjust the computational complexity in the worst case to 8 multiplications per sample, when each partition block is 4x4 or 8x8, only 8 transform coefficients may be output after applying the forward LFNST. That is, if the partition block is 4x4, an 8x16 matrix may be applied as a transform matrix, and if the partition block is 8x8, an 8x48 matrix may be applied as a transform matrix.

Meanwhile, in the current VVC standard, LFNST index signaling is performed in units of coding units. Accordingly, in the case of ISP prediction mode and when LFNST is applied to all partition blocks, the same LFNST index value may be applied to the corresponding partition blocks. That is, once the LFNST index value is transmitted at the coding unit level, the corresponding LFNST index may be applied to all partition blocks inside the coding unit. As described above, the LFNST index value can have values of 0, 1, and 2, and 0 indicates a case where LFNST is not applied, and 1 and 2 are two transform matrices present in one LFNST set when LFNST is applied. Points to.

As described above, the LFNST set is determined by the intra prediction mode, and in the ISP prediction mode, all partition blocks in the coding unit are predicted by the same intra prediction mode, so the partition blocks may refer to the same LFNST set.

As another example, LFNST index signaling is still performed in units of coding units, but in the case of the ISP prediction mode, it is not uniformly determined whether to apply LFNST to all partition blocks, and for each partition block through a separate condition. It is possible to determine whether to apply the LFNST index value signaled at the coding unit level or not to apply the LFNST. Here, a separate condition may be signaled in the form of a flag for each partition block through the bitstream, and if the flag value is 1, the LFNST index value signaled at the coding unit level is applied, and if the flag value is 0, LFNST is not applied. May not.

Hereinafter, a method of maintaining the computational complexity for the worst case when applying LFNST to the ISP mode will be described.

In the ISP mode, when applying LFNST, the application of LFNST can be restricted to keep the number of multiplications per sample (or per coefficient, per position) below a certain value. Depending on the size of the partition block, the number of multiplications per sample (or per coefficient, per position) can be kept to 8 or less by applying LFNST as follows.

1. When both the horizontal and vertical lengths of the partition block are 4 or more, the same method as the worst case calculation complexity adjustment method for LFNST in the current VVC standard can be applied.

That is, if the partition block is a 4x4 block, instead of a 16x16 matrix, an 8x16 matrix that samples the top 8 rows from a 16x16 matrix in the forward direction can be applied, and a 16x8 matrix that samples the left 8 columns from a 16x16 matrix in the reverse direction can be applied. have. In addition, when the partition block is an 8x8 block, an 8x48 matrix obtained by sampling the top 8 rows from a 16x48 matrix is applied instead of a 16x48 matrix in the forward direction, and a 48x8 matrix sampled from the left 8 columns from a 48x16 matrix instead of a 48x16 matrix in the reverse direction. Can be applied.

In the case of a 4xN or Nx4 (N> 4) block, 16 coefficients generated after applying a 16x16 matrix to only the upper left 4x4 block when performing forward transformation are arranged in the upper left 4x4 area, and the other areas may be filled with 0 values. . In addition, when performing the reverse transformation, 16 coefficients located in the upper left 4x4 block may be arranged in a scanning order to form an input vector, and then 16x16 matrices may be multiplied to generate 16 output data. The generated output data is disposed in the upper left 4x4 area, and the rest area except for the upper left 4x4 area may be filled with zeros.

In the case of an 8xN or Nx8 (N> 8) block, 16 generated after applying a 16x48 matrix to only the ROI area inside the upper left 8x8 block (remaining areas excluding the upper left 8x8 block to the lower right 4x4 block) when performing forward conversion. The coefficients are arranged in the upper left 4x4 area, and all other areas may be filled with a value of 0. In addition, when performing the inverse transformation, an input vector is formed by arranging 16 coefficients located in the upper left 4x4 block according to the scanning order, and then 48 output data may be generated by multiplying a 48x16 matrix. The generated output data may be filled in the ROI area, and all other areas may be filled with a value of 0.

Another example is the number of multiplications per sample (or per coefficient, per position) based on the ISP coding unit size, not the size of the ISP partition block in order to keep the number of multiplications per sample (or per coefficient, per position) below a certain value. Can be kept to 8 or less. If there is only one block among the ISP partition blocks that satisfies the condition to which LFNST is applied, the complexity calculation for the worst case of LFNST may be applied based on the size of the corresponding coding unit rather than the size of the partition block. For example, if the luma coding block for a certain coding unit is divided into 4 partition blocks of 4x4 size and coded by the ISP, and there are no non-zero transform coefficients for 2 of the partition blocks, the other 2 partitions Blocks can be set to generate 16 transform coefficients instead of 8 each (based on the encoder).

Hereinafter, a method of signaling an LFNST index in the ISP mode will be described.

As described above, the LFNST index may have values of 0, 1, and 2, and 0 indicates that LFNST is not applied, and 1 and 2 indicate any one of two LFNST kernel matrices included in the selected LFNST set. LFNST is applied based on the LFNST kernel matrix selected by the LFNST index. The following describes how the LFNST index is transmitted in the current VVC standard.

1. The LFNST index may be transmitted once per coding unit (CU), and in the case of a dual-tree, individual LFNST indexes may be signaled for each luma block and chroma block.

2. When the LFNST index is not signaled, the LFNST index value is set to a default value of 0 (infer). The case where the LFNST index value is inferred to be 0 is as follows.

A. In the case of a mode in which transformation is not applied (e.g., transform skip, BDPCM, lossless coding, etc.)

B. When the primary transformation is not DCT-2 (DST7 or DCT8), that is, when the horizontal or vertical transformation is not DCT-2

C. When the horizontal or vertical length of the luma block of the coding unit exceeds the size of the maximum luma transform that can be transformed, for example, when the maximum luma transform size that can be transformed is 64, the luma block of the coding block is If the size is equal to 128x16, LFNST cannot be applied.

In the case of the dual tree, it is determined whether the size of the maximum luma transform is exceeded for each of the coding units for the luma component and the coding units for the chroma component. That is, whether the luma block exceeds the maximum luma transform size that can be transformed is checked, and for the chroma block, the horizontal/vertical length of the corresponding luma block for the color format and the maximum luma transform size that can be transformed are exceeded. Whether or not it is checked. For example, when the color format is 4:2:0, the horizontal/vertical length of the corresponding luma block is twice the corresponding chroma block, and the transform size of the corresponding luma block is twice the corresponding chroma block. As another example, when the color format is 4:4:4, the horizontal/vertical length and the transform size of the corresponding luma block are the same as the corresponding chroma block.

A 64-length conversion or a 32-length conversion means a conversion applied to a width or length having a length of 64 or 32, respectively, and "conversion size" may mean a corresponding length of 64 or 32.

In the case of a single tree, it is checked whether the horizontal length or the vertical length of the luma block exceeds the maximum luma transform block size that can be converted, and if it exceeds, LFNST index signaling may be omitted.

D. The LFNST index can be transmitted only when both the horizontal length and the vertical length of the coding unit are 4 or more.

In the case of a dual tree, the LFNST index can be signaled only when both the horizontal length and the vertical length of the corresponding component (ie, luma or chroma component) are 4 or more.

In the case of a single tree, the LFNST index may be signaled when both the horizontal length and the vertical length of the luma component are 4 or more.

E. If the last non-zero coefficient position is not the DC position (the upper-left position of the block), if the dual-tree type luma block, the last non-zero coefficient position is not the DC position, LFNST Transfer the index. In the case of a dual tree type chroma block, the LNFST index is transmitted if at least one of the last non-zero coefficient position for Cb and the last non-zero coefficient position for Cr is not a DC position.

In the case of a single tree type, if the last non-zero coefficient position in any of the luma component, Cb component, and Cr component is not the DC position, the LFNST index is transmitted.

Here, if the CBF (coded block flag) value indicating whether a transform coefficient exists for one transform block is 0, the position of the last non-zero coefficient for the corresponding transform block is not checked to determine whether the LFNST index is signaled. That is, when the CBF value is 0, since transformation is not applied to the corresponding block, the position of the last non-zero coefficient may not be considered when checking the condition for LFNST index signaling.

For example, 1) In case of dual tree type and luma component, if the corresponding CBF value is 0, LFNST index is not signaled. 2) In case of dual tree type and chroma component, CBF value for Cb is 0 and CBF value for Cr is 1 In this case, only the position of the last non-zero coefficient for Cr is checked and the corresponding LFNST index is transmitted. 3) In the case of a single tree type, only the components with each CBF value of 1 for luma, Cb, and Cr are the last non-zero. The position of the coefficient is checked.

F. When it is confirmed that the transform coefficient exists at a location other than the location where the LFNST transform coefficient can exist, the LFNST index signaling can be omitted. In the case of a 4x4 transform block and an 8x8 transform block, LFNST transform coefficients may exist in eight positions from the DC position according to the transform coefficient scanning order in the VVC standard, and all remaining positions are filled with zeros. In addition, in the case of the 4x4 transform block and the 8x8 transform block, LFNST transform coefficients may exist at 16 positions from the DC position according to the transform coefficient scanning order in the VVC standard, and all remaining positions are filled with zeros.

Therefore, if a non-zero transform coefficient exists in a region where the zero value should be filled after performing residual coding, LFNST index signaling can be omitted.

Meanwhile, the ISP mode may be applied only to a luma block or may be applied to both a luma block and a chroma block. As described above, when ISP prediction is applied, a corresponding coding unit is divided into two or four partition blocks to be predicted, and a transform may be applied to the corresponding partition blocks, respectively. Therefore, when determining the condition for signaling the LFNST index in units of coding units, it is necessary to take into account the fact that LFNST can be applied to each of the corresponding partition blocks. In addition, when the ISP prediction mode is applied only to a specific component (eg, a luma block), the LFNST index must be signaled in consideration of the fact that only the corresponding component is divided into partition blocks. LFNST index signaling methods available in ISP mode are summarized as follows.

B. When the horizontal or vertical length of the luma block of the coding unit exceeds the size of the maximum luma transform that can be transformed, for example, when the maximum luma transform size that can be transformed is 64, the luma block of the coding block is If the size is equal to 128x16, LFNST cannot be applied.

It is also possible to determine whether to signal the LFNST index based on the size of the partition block instead of the coding unit. That is, if the horizontal length or the vertical length of the partition block for the corresponding luma block exceeds the size of the maximum luma transform that can be transformed, LFNST index signaling may be omitted and the LFNST index value may be inferred as 0.

In the case of a dual tree, it is determined whether the maximum transform block size is exceeded for each of the coding unit or partition block for the luma component and the coding unit or partition block for the chroma component. That is, if the horizontal and vertical lengths of the coding unit or partition block for luma are compared with the maximum luma transform size, respectively, if any one is greater than the maximum luma transform size, LFNST is not applied, and in the case of the coding unit or partition block for chroma, the color The horizontal/vertical length of the corresponding luma block for the format and the size of the maximum luma transform capable of maximum conversion are compared. For example, when the color format is 4:2:0, the horizontal/vertical length of the corresponding luma block is twice the corresponding chroma block, and the transform size of the corresponding luma block is twice the corresponding chroma block. As another example, when the color format is 4:4:4, the horizontal/vertical length and the transform size of the corresponding luma block are the same as the corresponding chroma block.

In the case of a single tree, it is checked whether the horizontal or vertical length of the luma block (coding unit or partition block) exceeds the maximum luma transform block size that can be converted, and if it exceeds, LFNST index signaling can be omitted. .

C. If LFNST included in the current VVC standard is applied, the LFNST index can be transmitted only when both the horizontal length and the vertical length of the partition block are 4 or more.

If the LFNST for a 2xM (1xM) or Mx2 (Mx1) block is applied in addition to the LFNST included in the current VVC standard, the LFNST index is only used when the size of the partition block is equal to or greater than the 2xM (1xM) or Mx2 (Mx1) block. Can be transmitted. Here, when the PxQ block is equal to or greater than the RxS block, it means that P≥R and Q≥S.

In summary, the LFNST index can be transmitted only when the partition block is equal to or larger than the minimum size applicable to the LFNST. In the case of a dual tree, the LFNST index can be signaled only when the partition block for the luma or chroma component is equal to or larger than the minimum size to which LFNST is applicable. In the case of a single tree, the LFNST index can be signaled only when the partition block for the luma component is equal to or larger than the minimum size applicable to the LFNST.

In this document, when an MxN block is greater than or equal to a KxL block, it means that M is greater than or equal to K and N is greater than or equal to L. That the MxN block is greater than the KxL block means that M is greater than or equal to K and N is greater than or equal to L, and M is greater than K or N is greater than L. When an MxN block is less than or equal to a KxL block, it means that M is less than or equal to K and N is less than or equal to L, and that an MxN block is less than or equal to a KxL block means that M is less than or equal to K and N is less than L. It is equal to or equal to, meaning that M is less than K or N is less than L.

D. If the last non-zero coefficient position is not the DC position (the upper-left position of the block), if it is a dual-tree type luma block, even one of all partition blocks is the last non-zero coefficient. If the location of is not the DC location, LFNST can be transmitted. If it is a dual tree type and is a chroma block, all partition blocks for Cb (if ISP mode is not applied to the chroma component, the number of partition blocks is considered to be one), the position of the last non-zero coefficient and all partitions for Cr. The LNFST index can be transmitted if at least one of the positions of the last non-zero coefficients is not a DC position (if the ISP mode is not applied to the chroma component, the number of partition blocks is considered to be one).

In the case of a single tree type, even one of all partition blocks for a luma component, a Cb component, and a Cr component may transmit a corresponding LFNST index if the position of the last non-zero coefficient is not the DC position.

Here, if the CBF (coded block flag) value indicating whether the transform coefficient exists for each partition block is 0, the position of the last non-zero coefficient for the corresponding partition block is not checked in order to determine whether the LFNST index is signaled. That is, when the CBF value is 0, the transform is not applied to the corresponding block. Therefore, when checking the condition for LFNST index signaling, the position of the last non-zero coefficient for the corresponding partition block is not considered.

For example, 1) In the case of a dual tree type and a luma component, if the CBF value for each partition block is 0, the corresponding partition block is excluded when determining whether to signal the LFNST index, and 2) when the dual tree type is a chroma component, each partition block is For a partition block, if the CBF value for Cb is 0 and the CBF value for Cr is 1, only the position of the last non-zero coefficient for Cr is checked to determine whether to signal the corresponding LFNST index. 3) In the case of a single tree type, the luma component For all partition blocks of the, Cb and Cr components, the position of the last non-zero coefficient may be checked only for blocks having a CBF value of 1 to determine whether to signal the LFNST index.

In the case of the ISP mode, image information may be configured so that the position of the last non-zero coefficient is not checked, and an embodiment of this is as follows.

i. In the case of the ISP mode, LFNST index signaling may be allowed without checking the position of the last non-zero coefficient for both the luma block and the chroma block. That is, even if the position of the last non-zero coefficient for all partition blocks is the DC position or the corresponding CBF value is 0, the corresponding LFNST index signaling can be allowed.

ii. In the ISP mode, the check for the position of the last non-zero coefficient may be omitted for only the luma block, and in the case of the chroma block, the position of the last non-zero coefficient in the above-described scheme may be checked. For example, in the case of a dual tree type and a luma block, LFNST index signaling is allowed without checking the position of the last non-zero coefficient. In the case of a dual tree type and a chroma block, the last non-zero It is possible to determine whether to signal the corresponding LFNST index by checking whether there is a DC position relative to the position of the coefficient.

iii. In the case of ISP mode and single tree type, the method i or ii may be applied. That is, in the case of ISP mode and applying number i to the single tree type, the check for the position of the last non-zero coefficient for both the luma block and the chroma block may be omitted, and LFNST index signaling may be allowed. Alternatively, ii is applied to omit the check for the position of the last non-zero coefficient for the partition blocks for the luma component, and the partition blocks for the chroma component (if ISP is not applied for the chroma component, the partition block For example, the number may be considered to be 1), it is possible to determine whether to signal the corresponding LFNST index by performing a check on the position of the last non-zero coefficient in the above-described manner.

E. LFNST index signaling can be omitted when it is confirmed that a transform coefficient exists in a location other than a location where the LFNST transform coefficient can exist even for one of all partition blocks.

For example, in the case of a 4x4 partition block and an 8x8 partition block, LFNST transform coefficients may exist in eight positions from the DC position according to the transform coefficient scanning order in the VVC standard, and all remaining positions are filled with zeros. In addition, in the case of equal to or greater than 4x4 but not a 4x4 partition block and an 8x8 partition block, LFNST transform coefficients may exist at 16 positions from the DC position according to the transform coefficient scanning order in the VVC standard, and all remaining positions are filled with zeros. You lose.

Meanwhile, in the case of the ISP mode, in the current VVC standard, the length condition is independently viewed for the horizontal direction and the vertical direction, and DST-7 is applied instead of DCT-2 without signaling for the MTS index. It is determined whether the horizontal or vertical length is greater than or equal to 4 and less than or equal to 16, and a first-order transformation kernel is determined according to the determination result. Accordingly, in the case where LFNST can be applied while in the ISP mode, the following conversion combination configuration is possible.

1. When the LFNST index is 0 (including the case in which the LFNST index is inferred as 0), the first-order conversion decision condition when the ISP included in the current VVC standard can be followed. In other words, each of the horizontal and vertical directions independently checks whether the length condition (a condition equal to or greater than 4 and equal to or less than 16) is satisfied, and if it is satisfied, DST-7 is used instead of DCT-2 for first-order transformation. If applicable and not satisfied, DCT-2 can be applied.

2. When the LFNST index is greater than 0, the following two configurations can be made as a first-order conversion.

A. DCT-2 can be applied to both horizontal and vertical directions.

B. The conditions for determining the first-order conversion when the ISP included in the current VVC standard can be followed. In other words, it checks whether the length condition (a condition equal to or greater than 4 and equal to or less than 16) is satisfied independently for the horizontal and vertical directions, and if it is satisfied, DST-7 is applied instead of DCT-2, and if not, DCT-2 can be applied.

In the ISP mode, the LFNST index may be configured to be transmitted for each partition block rather than for each coding unit. In this case, in the above-described LFNST index signaling scheme, it is considered that only one partition block exists in the unit in which the LFNST index is transmitted, and whether to signal the LFNST index may be determined.

Meanwhile, the following describes the signaling order of the LFNST index and the MTS index.

According to an example, the LFNST index signaled in residual coding may be coded after the coding position for the last non-zero coefficient position, and the MTS index may be coded immediately after the LFNST index. In this configuration, the LFNST index may be signaled for each conversion unit. Alternatively, even if not signaled in residual coding, the LFNST index may be coded after coding for the last significant coefficient position, and the MTS index may be coded after the LFNST index.

The syntax of residual coding according to an example is as follows.

The meanings of the main variables shown in Table 3 are as follows.

1. cbWidth, cbHeight: width and height of the current coding block

2. log2TbWidth, log2TbHeight: The log value of base-2 and zero-out for the width and height of the current transform block are reflected and reduced to the upper left area where non-zero coefficients can exist. I can.

3. sps_lfnst_enabled_flag: A flag indicating whether LFNST is applicable. If the flag value is 0, it indicates that LFNST is not applicable, and if the flag value is 1, it indicates that LFNST is applicable. It is defined in the Sequence Parameter Set (SPS).

4. CuPredMode[ chType ][ x0 ][ y0 ]: The prediction mode corresponding to the variable chType and (x0, y0) position, chType can have

values

0 and 1, 0 represents the luma component, and 1 represents the chroma component. . The (x0, y0) position represents the position on the picture, and as CuPredMode[chType][x0][y0] values, MODE_INTRA (intra prediction) and MODE_INTER (inter prediction) are possible.

5. IntraSubPartitionsSplit[ x0 ][ y0 ]: (x0, y0) The contents of the location are the same as in #4. This indicates which ISP division is applied at the (x0, y0) position, and ISP_NO_SPLIT indicates that the coding unit corresponding to the (x0, y0) position is not divided into partition blocks.

6. intra_mip_flag[ x0 ][ y0 ]: The contents of the (x0, y0) location are the same as in step 4 above. The intra_mip_flag is a flag indicating whether a matrix-based intra prediction (MIP) prediction mode is applied. If the flag value is 0, it indicates that MIP is not applicable, and if the flag value is 1, it indicates that the MIP is applied.

7. cIdx: A value of 0 represents luma, and a value of 1 and 2 represent chroma components Cb and Cr, respectively.

8. treeType: indicates single-tree and dual-tree (SINGLE_TREE: single tree, DUAL_TREE_LUMA: dual tree for luma components, DUAL_TREE_CHROMA: dual tree for chroma components)

9. tu_cbf_cb[ x0 ][ y0 ]: (x0, y0) The contents of the location are the same as in #4. Indicates CBF (Coded Block Flag) for the Cb component. If the value is 0, it means that a non-zero coefficient does not exist in the corresponding conversion unit for the Cb component, and if 1, the non-zero coefficient corresponds to the Cb component. Indicates that it exists in the transform unit.

10. lastSubBlock: indicates a position in the scan order of a sub-block (Coefficient Group (CG)) where the last non-zero coefficient is located. 0 indicates a sub-block including a DC component, and if greater than 0, it is not a sub-block including a DC component.

11. lastScanPos: This indicates where the last significant coefficient is in the scan order within one sub-block. If one sub-block consists of 16 positions, values from 0 to 15 are possible.

12. lfnst_idx[ x0 ][ y0 ]: LFNST index syntax element to be parsed. If it is not parsed, it is inferred as a value of 0. That is, the default value is set to 0 and indicates that LFNST is not applied.

13. LastSignificantCoeffX, LastSignificantCoeffY: The last significant coefficient represents the x-coordinate and y-coordinate located in the transform block. The x-coordinate starts at 0 and increases from left to right, and the y-coordinate starts at 0 and increases from top to bottom. If the values of both variables are 0, it means that the last significant coefficient is located in DC.

14. cu_sbt_flag: Flag indicating whether subblock transformation (SBT) included in the current VVC standard is applicable. If the flag value is 0, it indicates that SBT is not applicable, and if the flag value is 1, SBT is applied. To be.

15.sps_explicit_mts_inter_enabled_flag, sps_explicit_mts_intra_enabled_flag: flags indicating whether explicit MTS has been applied to the inter CU and intra CU, respectively.If the flag value is 0, it indicates that MTS is not applicable to the inter CU or intra CU, and if 1 is applicable. Indicates that.

16. tu_mts_idx[ x0 ][ y0 ]: This is an MTS index syntax element to be parsed. If it is not parsed, it is inferred as a value of 0. That is, the default value is set to 0, indicating that DCT-2 is applied to both the horizontal and vertical directions.

As shown in Table 3, in the case of a single tree, it is possible to determine whether to signal the LFNST index with only the last significant coefficient position condition for luma. That is, if the last significant coefficient position is not DC and the last significant coefficient exists in the upper left sub-block (CG), for example, a 4x4 block, the LFNST index is signaled. In this case, in the case of the 4x4 transform block and the 8x8 transform block, the LFNST index is signaled only when the last significant coefficient exists at positions 0 to 7 in the upper left sub-block.

In the case of the dual tree, the LFNST index is signaled independently of each of the luma and the chroma, and in the case of the chroma, the LFNST index may be signaled by applying the last significant coefficient position condition only to the Cb component. For the Cr component, a corresponding condition may not be checked, and if the CBF value for Cb is 0, the LFNST index may be signaled by applying the last significant coefficient position condition to the Cr component.

'Min( log2TbWidth, log2TbHeight) >= 2'in Table 3 can be expressed as “Min( tbWidth, tbHeight) >= 4”, and'Min( log2TbWidth, log2TbHeight) >= 4'means “Min( tbWidth, tbHeight ) >= 16”.

In Table 3, log2ZoTbWidth and log2ZoTbHeight each mean a logarithmic value of which the base of the width and height of the upper left area where the last significant coefficient can exist by zero-out is 2 (base-2).

As shown in Table 3, log2ZoTbWidth and log2ZoTbHeight values can be updated in two places. The first is before the MTS index or LFNST index value is parsed, and the second is after the MTS index is parsed.

Since the first update is before the MTS index (tu_mts_idx[ x0 ][ y0 ]) value is parsed, log2ZoTbWidth and log2ZoTbHeight can be set regardless of the MTS index value.

After the MTS index is parsed, log2ZoTbWidth and log2ZoTbHeight are set when the MTS index value is greater than 0 (DST-7/DCT-8 combination). When DST-7/DCT-8 is independently applied to each of the horizontal and vertical directions in the first-order transformation, up to 16 effective coefficients may exist for each row or column for each direction. That is, after applying DST-7/DCT-8 having a length of 32 or more, up to 16 transform coefficients may be derived for each row or column from the left or the top. Therefore, for a 2D block, when DST-7/DCT-8 is applied in both the horizontal and vertical directions, effective coefficients may exist only up to the upper left 16x16 region.

In addition, when DCT-2 is applied independently to each of the horizontal and vertical directions in the current first-order transformation, up to 32 effective coefficients may exist for each row or column for each direction. That is, when DCT-2 with a length of 64 or more is applied, a maximum of 32 transform coefficients may be derived for each row or column from the left or the top. Therefore, for a 2D block, when DCT-2 is applied in both the horizontal and vertical directions, an effective coefficient may exist only up to the upper left 32x32 area.

In addition, when DST-7/DCT-8 is applied to one side and DCT-2 is applied to the horizontal and vertical directions, there may be 16 effective coefficients in the former direction, and 32 in the latter direction. There can be two effective coefficients. For example, if it is a 64x8 transform block and DCT-2 is applied in the horizontal direction and DST-7 is applied in the vertical direction (this may occur in a situation where the implicit MTS is applied), there may be an effective coefficient in the upper left 32x8 area. have.

If, as shown in Table 3, log2ZoTbWidth and log2ZoTbHeight are updated in two places, that is, before MTS index parsing, the ranges of last_sig_coeff_x_prefix and last_sig_coeff_y_prefix can be determined by log2ZoTbWidth and log2ZoTbHeight as shown in the table below.

In addition, in this case, the maximum values of last_sig_coeff_x_prefix and last_sig_coeff_y_prefix can be set by reflecting log2ZoTbWidth and log2ZoTbHeight values in the binarization process for last_sig_coeff_x_prefix and last_sig_coeff_y_prefix.

Meanwhile, according to an example, when LFNST is applied while in the ISP mode, when the signaling of Table 3 is applied, the specification text may be configured as shown in Table 6. Compared with Table 3, the condition that signaled the LFNST index only for non-ISP mode (IntraSubPartitionsSplit[ x0 ][ y0] = = ISP_NO_SPLIT in Table 3) has been deleted.

In the case of a single tree, if the LFNST index transmitted when luma (when cIdx = 0) is reused when chroma is, the LFNST index transmitted for the first ISP partition block in which the effective coefficient exists can be applied to the chroma transform block. . Alternatively, even in the case of a single tree, the LFNST index can be signaled separately from the luma component for the chroma component. The description of the variables listed in Table 6 is the same as in Table 3.

Meanwhile, according to an example, the LFNST index or/and the MTS index may be signaled at the coding unit level. As described above, the LFNST index can have three values, 0, 1, and 2, where 0 indicates that LFNST is not applied, and 1 and 2 are the first candidate and the first of the two LFNST kernel candidates included in the selected LFNST set, respectively. Indicate the second candidate. The LFNST index is coded through truncated unary binarization, and values 0, 1, and 2 may be coded as

empty strings

0, 10, and 11, respectively.

According to an example, LFNST may be applied only when DCT-2 is applied in both the horizontal direction and the vertical direction as a first-order transformation. Therefore, if the MTS index is signaled after LFNST index signaling, the MTS index can be signaled only when the LFNST index value is 0. If the LFNST index is not 0, the MTS index is not signaled and both the horizontal and vertical directions are DCT. First-order transformation can be performed by applying -2.

MTS index values can have values of 0, 1, 2, 3, 4, and 0, 1, 2, 3, 4 are DCT-2/DCT-2, DST-7/DST for horizontal and vertical directions, respectively. -7, DCT-8/DST-7, DST-7/DCT-8, DCT-8/DCT-8 can be indicated to be applied. Further, the MTS index may be coded through truncated unary binarization, and the 0, 1, 2, 3, and 4 values may be coded as

empty strings

0, 10, 110, 1110, and 1111, respectively.

Signaling of the LFNST index at the coding unit level may be represented as shown in the table below. The LFNST index may be signaled in the second half of the coding unit syntax table.

The variable LfnstDcOnly and the variable LfnstZeroOutSigCoeffFlag in Table 7 may be set as shown in Table 10 below.

The variable LfnstDcOnly is 1 if all of the last significant coefficients are located at the DC position (upper left position) for transform blocks with a value of 1 for the CBF (Coded Block Flag, 1 if there is at least one valid coefficient in the block, otherwise 0). If not, it is zero. More specifically, in the case of dual-tree luma, the position of the last significant coefficient is checked for one luma transform block, and in the case of dual-tree chroma, the position of the last significant coefficient is checked for both the transform block for Cb and the transform block for Cr. do. In the case of a single tree, the position of the last significant coefficient can be checked for the transform block for luma, Cb, and Cr.

The variable LfnstZeroOutSigCoeffFlag is 0 if there is an effective coefficient at the zero-out position when LFNST is applied, otherwise it is 1.

Lfnst_idx[x0][y0] included in Table 7 and the following tables indicates the LFNST index for the corresponding coding unit, and tu_mts_idx[x0][y0] indicates the MTS index for the corresponding coding unit.

According to an example, if the MTS index is to be continuously coded after the LFNST index at the coding unit level, a coding unit syntax table may be configured as shown in Table 8.

When comparing Table 8 with Table 7, under the condition of signaling lfnst_idx[ x0 ][ y0 ], the condition to check whether the value of tu_mts_idx[ x0 ][ y0] is 0 (that is, DCT-2 Checking whether or not) is changed to a condition that checks whether the transform_skip_flag[ x0 ][ y0] value is 0 (!transform_skip_flag[ x0 ][ y0 ]). transform_skip_flag[x0][y0] indicates whether the coding unit is coded in a transform skip mode in which transform is omitted, and the flag is signaled before the MTS index and LFNST index. That is, since lfnst_idx[x0][y0] is signaled before signaling the value of tu_mtx_idx[x0][y0], only the condition for the transform_skip_flag[x0][y0] value can be checked.

As shown in Table 8, several conditions are checked when coding tu_mts_idx[ x0 ][ y0 ], and tu_mts_idx[ x0 ][ y0] is signaled only when the value of lfnst_idx[ x0 ][ y0] is 0 as described above.

Further, tu_cbf_luma[x0][y0] is a flag indicating whether an effective coefficient exists for the luma component, and cbWidth and cbHeight represent the width and height of the coding unit for the luma component, respectively.

In addition, in Table 8, (IntraSubPartitionsSplit[ x0 ][ y0] = = ISP_NO_SPLIT) indicates a case that is not in the ISP mode, and (!cu_sbt_flag) indicates a case where SBT is not applied.

According to Table 8, tu_mts_idx[ x0 ][ y0] is signaled when both the width and height of the coding unit for the luma component are 32 or less, that is, whether MTS is applied is determined by the width and height of the coding unit for the luma component. do.

According to another example, when transform block tiling occurs (e.g., when the maximum transform size is set to 32, a 64x64 coding unit is divided into four 32x32 transform blocks and is coded) the size of each transform block The MTS index may be signaled based on. For example, when the width and height of a transform block are both 32 or less, the same MTS index value is applied to all transform blocks in a coding unit, so that the same first-order transform may be applied. In addition, if transform block tiling occurs, the value of tu_cbf_luma[ x0 ][ y0] in Table 8 is the CBF value for the upper left transform block, or 1 if the CBF value is 1 even for one transform block for all transform blocks. I can.

According to an example, when the ISP mode is applied to the current block, LFNST may be applied. In this case, Table 8 may be changed as shown in Table 9.

As shown in Table 9, even in ISP mode (IntraSubPartitionsSplitType! = ISP_NO_SPLIT) lfnst_idx[x0][y0] can be signaled, and the same LFNST index value can be applied to all ISP partition blocks.

In addition, as shown in Table 9, since tu_mts_idx[x0][y0] can be signaled only when not in the ISP mode, the MTS index coding part is the same as in Table 8.

As shown in Tables 8 and 9, when the MTS index is signaled immediately after the LFNST index, information on the first-order transformation cannot be known when performing residual coding. That is, the MTS index is signaled after residual coding. Accordingly, in the residual coding part, a portion that performs zero-out while leaving only 16 coefficients for a 32-length DST-7 or DCT-8 may be changed as shown in Table 10 below.

In the process of determining log2ZoTbWidth and log2ZoTbHeight as shown in Table 10 (where log2ZoTbWidth and log2ZoTbHeight each represent the base-2 log value of the width and height of the upper left area remaining after zero-out is performed) tu_mts_idx[ The part that checks the value of x0 ][y0] may be omitted.

Binarization for last_sig_coeff_x_prefix and last_sig_coeff_y_prefix in Table 10 may be determined based on log2ZoTbWidth and log2ZoTbHeight as shown in Table 5.

In addition, as shown in Table 10, a condition for checking sps_mts_enable_flag may be added when determining log2ZoTbWidth and log2ZoTbHeight in residual coding.

Meanwhile, according to another example, a coding unit syntax table, a transform unit syntax table, and a residual coding syntax table are as follows. According to Table 11, the MTS index moves from the transform unit level to the syntax of the coding unit level, and is signaled after LFNST index signaling. In addition, when the ISP is applied to the coding unit, the restriction condition that does not allow LFNST has been removed. When the ISP is applied to the coding unit, since the constraint condition not allowing LFNST is removed, LFNST can be applied to all intra prediction blocks. In addition, both the MTS index and the LFNST index are conditionally signaled at the last part of the coding unit level.

In Table 11, MtsZeroOutSigCoeffFlag is initially set to 1, and this value can be changed in the residual coding of Table 13. The variable MtsZeroOutSigCoeffFlag is changed from 1 to 0 when there is a significant coefficient in the region (LastSignificantCoeffX> 15 | | LastSignificantCoeffY> 15) that must be filled with zeros due to zero out, and in this case, as in Table 11, the MTS index Is not signaled.

Meanwhile, as shown in Table 11, when tu_cbf_luma[x0][y0] is 0, mts_idx[x0][y0] coding may be omitted. That is, if the CBF value of the luma component is 0, since no transformation is applied, there is no need to signal the MTS index, and thus the MTS index coding can be omitted.

According to an example, the technical feature may be implemented with another conditional syntax. For example, after MTS is performed, a variable indicating whether an effective coefficient exists in an area other than the DC area of the current block can be derived, and if the variable indicates that an effective coefficient exists in an area other than the DC area, MTS index can be signaled. That is, the existence of the effective coefficient in the region excluding the DC region of the current block indicates that the value of tu_cbf_luma[x0][y0] is 1, and in this case, the MTS index can be signaled.

The variable can be expressed as MtsDcOnly, and the variable MtsDcOnly is initially set to 1 at the coding unit level, and then the value is changed to 0 when the residual coding level indicates that an effective coefficient exists in a region other than the DC region of the current block. Can be. When the variable MtsDcOnly is 0, image information may be configured such that the MTS index is signaled.

If tu_cbf_luma[x0][y0] is 0, since the residual coding syntax is not called at the transform unit level of Table 12, the variable MtsDcOnly maintains an initial value of 1. In this case, since the variable MtsDcOnly has not been changed to 0, the video information may be configured so that the MTS index is not signaled. That is, the MTS index is not parsed and signaled.

Meanwhile, the decoding apparatus may determine the color index (cIdx) of the transform coefficient to derive the variable MtsZeroOutSigCoeffFlag of Table 13. When the color index (cIdx) is 0, it means the luma component.

According to an example, since MTS can be applied only to the luma component of the current block, the decoding apparatus can determine whether the color index is luma when deriving the variable MtsZeroOutSigCoeffFlag that determines whether to parse the MTS index (if cIdx = = 0, MtsZeroOutSigCoeffFlag = 0).

The variable MtsZeroOutSigCoeffFlag is a variable indicating whether zero-out has been performed when MTS is applied, and indicates whether a transform coefficient exists in an area other than the upper left 16X16 area in which the last significant coefficient can exist due to zero-out after MTS is performed. . The variable MtsZeroOutSigCoeffFlag is initially set to 1 at the coding unit level as shown in Table 11 (MtsZeroOutSigCoeffFlag = 1), and if there is a transform coefficient in a region other than the 16X16 region, the value is changed from 1 to 0 at the residual coding level as shown in Table 13. Can be changed (MtsZeroOutSigCoeffFlag = 0). If the value of the variable MtsZeroOutSigCoeffFlag is 0, the MTS index is not signaled.

As shown in Table 13, at the residual coding level, a non-zero-out region in which a non-zero transform coefficient may exist may be set depending on whether zero-out accompanying MTS has been performed. Even in this case, a color index (cIdx When) is 0, the non-zero-out area may be set as the upper left 16X16 area of the current block.

In this way, when deriving the variable that determines whether to parse the MTS index, it is determined whether the color component is luma or chroma, but since LFNST can be applied to both the luma component or chroma component of the current block, it is determined whether or not the LFNST index is parsed. When deriving the determining variable, the color component is not judged.

For example, Table 11 shows a variable LfnstZeroOutSigCoeffFlag that can indicate that zero-out has been performed when LFNST is applied. The variable LfnstZeroOutSigCoeffFlag indicates whether a valid coefficient exists in the second region excluding the first region at the top left of the current block. This value is initially set to 1, and if there is a valid coefficient in the second region, the value is 0. Can be changed to. The LFNST index can be parsed only when the initially set variable LfnstZeroOutSigCoeffFlag value is maintained as 1. When determining and deriving whether the variable LfnstZeroOutSigCoeffFlag value is 1, since LFNST can be applied to both the luma component or the chroma component of the current block, the color index of the current block is not determined.

12 is a diagram illustrating a block diagram of a CABAC encoding system according to an embodiment, and illustrates a block diagram of context-adaptive binary arithmetic coding (CABAC) for encoding a single syntax element.

In the encoding process of CABAC, first, when the input signal is a syntax element other than a binary value, the input signal is converted into a binary value through binarization. If the input signal is already a binary value, it is input to the bypass, that is, the encoding engine, without undergoing binarization. Here, each

binary number

0 or 1 constituting the binary value is called a bin. For example, if the binary string after binarization is 110, each of 1, 1, and 0 is referred to as one bin. The bin(s) for one syntax element may represent the value of the corresponding syntax element.

The binarized bins are input to a regular encoding engine or a bypass encoding engine.

The regular encoding engine allocates a model to a context that reflects a probability value for a corresponding bin, and encodes the bin based on the allocated context model. In the regular encoding engine, after encoding each bin, the probability model for the corresponding bin may be updated. Bins that are coded in this way are called context-coded bins.

The bypass encoding engine omits the procedure of estimating the probability of the input bin and the procedure of updating the probability model applied to the corresponding bin after encoding. Instead of allocating a context, a uniform probability distribution is applied to encode the input bins, thereby improving the encoding speed. Bins that are coded in this way are called bypass bins.

Entropy encoding may determine whether to perform encoding through a regular encoding engine or through a bypass encoding engine, and switch an encoding path. Entropy decoding performs the same process as encoding in the reverse order.

When the truncated unary code is applied as the binarization method for the LFNST index, the LFNST index consists of up to two bins, and the binary code for the possible LFNST index values 0, 1, 2 ) Is assigned 0, 10 and 11 respectively.

According to an example, context-based CABAC coding may be applied to the first bin of the LFNST index (regular coding), and bypass coding may be applied to the second bin.

Further, according to another example, context-based CABAC coding may be applied to both the first and second bins of the LFNST index. The table shows the allocation of ctxInc of the LFNST index according to the context coded bin.

As shown in Table 14, for the first bean (binIdx = 0), context 0 can be applied for a single tree, and context 1 can be applied for a non-single tree. In addition, as shown in Table 14, context 2 may be applied to the second bin (binIdx = 1). That is, two contexts can be assigned to the first bean, one context can be assigned to the second bean, and each context can be classified by a ctxInc value (0, 1, 2).

Here, a single tree means that the luma component and the chroma component are coded with the same coding structure. If the coding unit is divided while having the same coding structure, but the size of the coding unit is less than a certain threshold, and the luma component and the chroma component are coded with separate tree structures, the coding unit is regarded as a dual tree and is the first bin. Can determine the context of. That is, as shown in Table 14, context 1 can be assigned.

Alternatively, if the value of the variable treeType is assigned to SINGLE_TREE for the first bean, context 0 can be coded, otherwise, context 1 can be used.

According to an example, when only the first (or second) candidate among two LFNST kernel candidates is attempted in the encoding process, the LFNST index has two fixed blank values for the corresponding candidate (only the first candidate is tried. It may be coded as case 10 and may be coded as 11 when only the second candidate is attempted). In this case, if the second bin is coded as bypass, a fixed amount of bits is generated for the second bin even though the second bin has a fixed value (0 or 1), which can significantly increase the coding cost for the second bin. have. If the second bean is coded in a context method rather than bypass, if only one fixed LFNST kernel candidate is attempted, the corresponding fixed value (0 or 1) for the second bean is updated to a 100% probability. The coding cost can be significantly reduced. In summary, both bins for LFNST index coding are coded in a context method, so even if only one LFNST kernel candidate is fixed and applied during the encoding process, the coding efficiency is minimized compared to applying both candidates and the encoding complexity Because it can be reduced, it is possible to give a substantial degree of freedom in finding a performance-complexity trade-off in the encoding process.

The following drawings are prepared to describe a specific example of the present specification. Since the names of specific devices or names of specific signals/messages/fields described in the drawings are provided by way of example, the technical features of the present specification are not limited to the specific names used in the following drawings.

13 is a flowchart illustrating an operation of a video decoding apparatus according to an embodiment of the present document.

Each step disclosed in FIG. 13 is based on some of the contents described above in FIGS. 3 to 12. Accordingly, detailed descriptions overlapping with those described above in FIGS. 2 to 12 will be omitted or simplified.

The decoding apparatus 200 according to an embodiment may derive transform coefficients by performing residual coding based on residual information received from a bitstream (S1310).

The decoding apparatus 200 may decode information about quantized transform coefficients for a current block from a bitstream, and quantized transform coefficients for a target block based on information about quantized transform coefficients for the current block. Can derive them. Information on quantized transform coefficients for the target block may be included in a sequence parameter set (SPS) or a slice header, information on whether or not a simplified transform (RST) is applied, information on a simplification factor, At least one of information on the minimum transform size to which the simplified transform is applied, information on the maximum transform size to which the simplified transform is applied, the size of the simplified inverse transform, and information on a transform index indicating any one of transform kernel matrices included in the transform set It may include.

The decoding apparatus 200 may derive transform coefficients by performing inverse quantization on residual information for the current block, that is, quantized transform coefficients, and may arrange the derived transform coefficients in a predetermined scanning order.

Specifically, the derived transform coefficients may be arranged according to the reverse diagonal scan order in units of 4×4 blocks, and the transform coefficients in the 4×4 block may also be arranged according to the reverse diagonal scan order. That is, transform coefficients subjected to inverse quantization may be arranged according to a reverse scan order applied in a video codec such as in VVC or HEVC.

The transform coefficient derived based on such residual information may be an inverse quantized transform coefficient as described above, or may be a quantized transform coefficient. That is, the transform coefficient may be data capable of checking whether the current block is non-zero data regardless of whether or not quantization is performed.

The decoding apparatus may derive a residual sample by applying an inverse transform to the quantized transform coefficient.

As described above, the decoding apparatus may derive a residual sample by applying LFNST as a non-separated transform or MTS as a separating transform, and these transforms indicate the LFNST kernel, that is, the LFNST index and the MTS kernel indicating the LFNST matrix, respectively. It may be performed based on the MTS index.

In addition, the decoding apparatus may further receive information on an intra prediction mode for the current block and an LFNST index (S1320).

This information is received as syntax information, and the syntax information is received as a binarized empty string containing 0s and 1s.

The decoding apparatus may derive binarization information for the syntax element of the LFNST index. This creates a candidate set for the binarized value that the syntax element of the received transform index may have. According to the present embodiment, the syntax element of the LFNST index may be binarized using a truncated universal code method.

The syntax element of the conversion index according to the present embodiment may indicate whether LFNST is applied and any one of the LFNST kernels included in the LFNST conversion set. When the LFNST conversion set includes two LFNST kernels, the LFNST index There can be three values of the syntax element.

That is, according to an embodiment, the syntax element value for the LFNST index is 0 indicating when LFNST is not applied to the current block, 1 indicating the first LFNST kernel among LFNST kernels, and the second LFNST kernel among LFNST kernels. It may contain 2 indicating.

In this case, the syntax element values for the three LFNST indices may be coded as 0, 10, and 11 according to the truncated universal code method. That is, a value of 0 for a syntax element may be binarized to '0', a value of 1 for a syntax element may be '10', and a value of 2 for a syntax element may be binarized to '11'.

Meanwhile, the decoding apparatus may derive context information for the first bin and the second of the LFNST index (S1330), and decode bins of the syntax element bin string based on the context information (S1340).

Depending on the tree type of the current block, context information for the first bin may be derived as a different value. For example, if the tree type of the current block is a single tree, the first bin may be derived as first context information, and if the tree type of the current block is not a single tree, the first bin may be derived as second context information.

Meanwhile, the context information for the second bin may be derived as one value regardless of the tree type of the current block. That is, according to an example, the bin string of the LFNST index may be decoded based on a context model rather than a bypass method for both bins.

In summary, the decoding apparatus receives an bin string that has been binarized using a truncated universal code method, and decodes a syntax element of the LFNST index based on context information.

A value of the syntax element for the LFNST index applied to the current block may be derived from among the binarized values that the syntax element of the LFNST index may have by such context information-based decoding (S1350).

That is, it can be derived whether any one of the

LFNST indexes

0, 1, and 2 is applied to the current target block.

The decoding apparatus 200 determines the LFNST transform set based on the mapping relationship according to the intra prediction mode applied to the current block (S1360), and based on the LFNST transform set, the LFNST kernel and LFNST index included in the LFNST transform set. A modified transform coefficient may be derived by applying LFNST (S1370).

Thereafter, the decoding apparatus may derive residual samples for the current block based on the inverse linear transformation of the modified transform coefficients (S1380), and may generate a reconstructed picture based on the residual samples (S1390). .

14 is a flowchart illustrating an operation of a video encoding apparatus according to an embodiment of the present document.

Each step disclosed in FIG. 14 is based on some of the contents described above in FIGS. 3 to 12. Accordingly, detailed descriptions overlapping with those described above in FIGS. 1 and 3 to 12 will be omitted or simplified.

The encoding apparatus 100 according to an embodiment may derive a prediction sample for a current block based on an intra prediction mode applied to the current block (S1410).

The encoding apparatus 100 may derive residual samples for the current block based on the prediction samples (S1420).

The encoding apparatus 100 may derive transform coefficients for the current block by applying at least one of LFNST or MTS to residual samples, and arrange the transform coefficients according to a predetermined scanning order.

The encoding apparatus may derive a transform coefficient for the current block based on the first transform for the residual sample (S1430).

The first-order transform may be performed through a plurality of transform kernels, such as MTS, and in this case, a transform kernel may be selected based on an intra prediction mode.

After deriving the transform coefficient by applying the MTS, the encoding apparatus may zero out the remaining area of the current block excluding the upper left specific area of the current block, for example, a 16x16 area.

In addition, the encoding apparatus 100 determines whether to perform quadratic transformation or non-separated transformation, specifically LFNST on the transform coefficients for the current block, and derives the modified transform coefficients by applying LFNST to the transform coefficient. can do. Specifically, the encoding device may derive a modified transform coefficient by applying LFNST based on the LFNST transform set and the LFNST kernel included in the LFNST transform set (S1440).

LFNST is a non-separated transform that applies a transform without separating the coefficients in a specific direction, unlike a first-order transform that transforms coefficients to be transformed in a vertical or horizontal direction. The non-separated transformation may be a low-frequency non-separated transformation in which the transformation is applied only to a low frequency region, not the entire target block to be transformed.

The encoding device may encode at least one of an LFNST index indicating an LFNST kernel or an MTS index indicating an MTS kernel.

First, the encoding device may derive a value of the syntax element for the LFNST index (S1450) and may binarize the value of the syntax element for the LFNST index (S1460).

The syntax element of the LFNST index according to the present embodiment may indicate whether LFNST is applied and any one of the LFNST kernels included in the LFNST transformation set. When the LFNST transformation set includes two LFNST kernels, the LFNST index There can be three values of the syntax element.

According to an embodiment, the syntax element value for the LFNST index is 0 indicating when LFNST is not applied to the current block, 1 indicating the first LFNST kernel among LFNST kernels, and 1 indicating the second LFNST kernel among LFNST kernels. It can be derived as 2.

The encoding device may binarize the values of the syntax elements for the three transform indices into 0, 10, and 11 according to the truncated universal code method. That is, the value 0 for the syntax element can be binarized to '0', the value 1 for the syntax element is '10', and the value 2 for the syntax element can be binarized to '11'. For the syntax element for Korea, it can be binarized to any one of '0', '10, and '11'.

The encoding device may derive context information for the first bin and the second of the LFNST index (S1470), and encode the bins of the syntax element bean string based on the context information (S1480).

Meanwhile, the context information for the second bin may be derived as one value regardless of the tree type of the current block. That is, according to an example, the bin string of the LFNST index may be encoded based on a context model rather than a bypass method for both bins.

In summary, the encoding device binarizes the empty string of the LFNST index using a truncated universal code method, and encodes the syntax element of the LFNST index for the corresponding binarization value based on different context information.

The encoding device may configure and output video information such that at least one of the LFNST index and the MTS index is signaled at the coding unit level, and the MTS index is signaled immediately after signaling of the LFNST index, and output after encoding the quantized residual information. Yes (S1490).

In addition, the encoding apparatus may perform quantization based on transform coefficients or modified transform coefficients for the current block to derive quantized transform coefficients, and encode and output image information including information on the quantized transform coefficients. have.

The encoding apparatus may generate residual information including information on quantized transform coefficients. The residual information may include the above-described conversion related information/syntax element. The encoding device may encode image/video information including residual information and output it in the form of a bitstream.

More specifically, the encoding apparatus may generate information about quantized transform coefficients and encode information about the generated quantized transform coefficients.

In this document, at least one of quantization/inverse quantization and/or transform/inverse transformation may be omitted. When the quantization/inverse quantization is omitted, the quantized transform coefficient may be referred to as a transform coefficient. When the transform/inverse transform is omitted, the transform coefficient may be referred to as a coefficient or a residual coefficient, or may still be referred to as a transform coefficient for uniformity of expression.

In addition, in this document, the quantized transform coefficient and the transform coefficient may be referred to as a transform coefficient and a scaled transform coefficient, respectively. In this case, the residual information may include information about the transform coefficient(s), and the information about the transform coefficient(s) may be signaled through a residual coding syntax. Transform coefficients may be derived based on the residual information (or information about the transform coefficient(s)), and scaled transform coefficients may be derived through an inverse transform (scaling) of the transform coefficients. Residual samples may be derived based on the inverse transform (transform) of the scaled transform coefficients. This may be applied/expressed in other parts of this document as well.

In the above-described embodiment, the methods are described on the basis of a flowchart as a series of steps or blocks, but this document is not limited to the order of steps, and certain steps may occur in a different order or concurrently with the steps described above. have. In addition, those skilled in the art will appreciate that the steps shown in the flowchart are not exclusive, other steps may be included, or one or more steps in the flowchart may be deleted without affecting the scope of this document.

The above-described method according to this document may be implemented in the form of software, and the encoding device and/or the decoding device according to this document performs image processing such as, for example, a TV, computer, smartphone, set-top box, and display device. It can be included in the device.

In this document, when the embodiments are implemented as software, the above-described method may be implemented as a module (process, function, etc.) that performs the above-described functions. Modules are stored in memory and can be executed by a processor. The memory may be inside or outside the processor, and may be connected to the processor through various well-known means. The processor may include an application-specific integrated circuit (ASIC), another chipset, a logic circuit, and/or a data processing device. The memory may include read-only memory (ROM), random access memory (RAM), flash memory, memory card, storage medium, and/or other storage device. That is, the embodiments described in this document may be implemented and performed on a processor, microprocessor, controller, or chip. For example, the functional units shown in each drawing may be implemented and executed on a computer, a processor, a microprocessor, a controller, or a chip.

In addition, the decoding device and encoding device to which this document is applied include a multimedia broadcasting transmission/reception device, a mobile communication terminal, a home cinema video device, a digital cinema video device, a surveillance camera, a video chat device, a real-time communication device such as video communication, and mobile streaming. Devices, storage media, camcorders, video-on-demand (VoD) service providers, OTT video (Over the top video) devices, Internet streaming service providers, three-dimensional (3D) video devices, video telephony video devices, and medical video devices, etc. It may be included, and may be used to process a video signal or a data signal. For example, an OTT video (Over the top video) device may include a game console, a Blu-ray player, an Internet-connected TV, a home theater system, a smartphone, a tablet PC, and a digital video recorder (DVR).

In addition, the processing method to which this document is applied may be produced in the form of a program executed by a computer, and may be stored in a computer-readable recording medium. Multimedia data having a data structure according to this document can also be stored in a computer-readable recording medium. The computer-readable recording medium includes all kinds of storage devices and distributed storage devices in which computer-readable data is stored. The computer-readable recording medium is, for example, Blu-ray disk (BD), universal serial bus (USB), ROM, PROM, EPROM, EEPROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical It may include a data storage device. In addition, the computer-readable recording medium includes media implemented in the form of a carrier wave (for example, transmission through the Internet). In addition, the bitstream generated by the encoding method may be stored in a computer-readable recording medium or transmitted through a wired or wireless communication network. Further, an embodiment of this document may be implemented as a computer program product using a program code, and the program code may be executed in a computer according to the embodiment of the present document. The program code may be stored on a carrier readable by a computer.

Referring to FIG. 15, a video/image coding system may include a source device and a reception device. The source device may transmit the encoded video/image information or data in a file or streaming form to the receiving device through a digital storage medium or a network.

The source device may include a video source, an encoding device, and a transmission unit. The receiving device may include a receiving unit, a decoding device, and a renderer. The encoding device may be referred to as a video/image encoding device, and the decoding device may be referred to as a video/image decoding device. The transmitter may be included in the encoding device. The receiver may be included in the decoding device. The renderer may include a display unit, and the display unit may be configured as a separate device or an external component.

The video source may acquire a video/image through a process of capturing, synthesizing, or generating a video/image. The video source may include a video/image capturing device and/or a video/image generating device. The video/image capture device may include, for example, one or more cameras, a video/image archive including previously captured video/images, and the like. The video/image generating device may include, for example, a computer, a tablet and a smartphone, and may (electronically) generate a video/image. For example, a virtual video/image may be generated through a computer or the like, and in this case, a video/image capturing process may be substituted as a process of generating related data.

The encoding device may encode the input video/video. The encoding apparatus may perform a series of procedures such as prediction, transformation, and quantization for compression and coding efficiency. The encoded data (encoded video/video information) may be output in the form of a bitstream.

The transmission unit may transmit the encoded video/video information or data output in the form of a bitstream to the reception unit of the reception device through a digital storage medium or a network in a file or streaming format. Digital storage media may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, and SSD. The transmission unit may include an element for generating a media file through a predetermined file format, and may include an element for transmission through a broadcast/communication network. The receiver may receive/extract the bitstream and transmit it to the decoding device.

The decoding device may decode the video/image by performing a series of procedures such as inverse quantization, inverse transformation, and prediction corresponding to the operation of the encoding device.

The renderer can render the decoded video/image. The rendered video/image may be displayed through the display unit.

In addition, the content streaming system to which this document is applied may largely include an encoding server, a streaming server, a web server, a media storage device, a user device, and a multimedia input device.

The encoding server serves to generate a bitstream by compressing content input from multimedia input devices such as smartphones, cameras, camcorders, etc. into digital data, and transmits it to the streaming server. As another example, when multimedia input devices such as smartphones, cameras, camcorders, etc. directly generate bitstreams, the encoding server may be omitted. The bitstream may be generated by an encoding method or a bitstream generation method to which this document is applied, and the streaming server may temporarily store the bitstream while transmitting or receiving the bitstream.

The streaming server transmits multimedia data to a user device based on a user request through a web server, and the web server serves as an intermediary for notifying the user of a service. When a user requests a desired service from the web server, the web server transmits it to the streaming server, and the streaming server transmits multimedia data to the user. In this case, the content streaming system may include a separate control server. In this case, the control server serves to control a command/response between devices in the content streaming system.

The streaming server may receive content from a media storage and/or encoding server. For example, when content is received from the encoding server, the content may be received in real time. In this case, in order to provide a smooth streaming service, the streaming server may store the bitstream for a predetermined time.

Examples of the user device include a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation system, a slate PC, and Tablet PC, ultrabook, wearable device, e.g., smartwatch, smart glass, head mounted display (HMD), digital TV, desktop computer , Digital signage, etc. Each server in the content streaming system may be operated as a distributed server, and in this case, data received from each server may be distributedly processed.

The claims set forth herein may be combined in a variety of ways. For example, the technical features of the method claims of the present specification may be combined to be implemented as a device, and the technical features of the device claims of the present specification may be combined to be implemented by a method. In addition, the technical characteristics of the method claim of the present specification and the technical characteristics of the device claim may be combined to be implemented as a device, and the technical characteristics of the method claim of the present specification and the technical characteristics of the device claim may be combined to be implemented by a method.

Claims

In the video decoding method performed by the decoding device,

Deriving a transform coefficient for the current block based on residual information for the current block;

Deriving a modified transform coefficient by applying LFNST to the transform coefficient;

Deriving residual samples for the current block based on the inverse linear transform of the modified transform coefficients; And

Including the step of generating a reconstructed picture based on the residual samples,

The LFNST is performed based on an LFNST transform set, an LFNST kernel included in the LFNST transform set, and an LFNST index indicating the LFNST kernel,

A video decoding method, characterized in that the first bin and the second bin of the syntax element bin string for the LFNST index are decoded using a context coding method.
The method of claim 1,

Deriving context information of a syntax element for the LFNST index;

Decoding bins of a syntax element bin string for the LFNST index based on the context information;

And deriving a value of a syntax element for the LFNST index.
The method of claim 2,

The image decoding method, characterized in that the context information for the first bin is derived as a different value according to the tree type of the current block.
The method of claim 3,

If the tree type of the current block is a single tree, the first bin is derived as first context information,

If the tree type of the current block is not a single tree, the first bin is derived as second context information.
The method of claim 4,

Regardless of the tree type of the current block, context information for the second bin is derived with the same value.
The method of claim 2,

The LFNST transform set includes two LFNST kernels,

The value of the syntax element is 0 indicating a case in which the LFNST is not applied to the current block, 1 indicating a first LFNST kernel among the LFNST kernels, and 2 indicating a second LFNST kernel among the LFNST kernels. Video decoding method comprising one.
The method of claim 6,

The value of the syntax element is binarized into a truncated binary code,

A value of 0 for the syntax element is '0', a value of 1 for the syntax element is '10', and a value of 2 for the syntax element is binarized to '11'.
In the video encoding method performed by the video encoding device,

Deriving prediction samples for the current block;

Deriving residual samples for the current block based on the prediction sample;

Deriving transform coefficients for the current block based on a first-order transform for the residual sample;

Deriving a modified transform coefficient by applying LFNST to the transform coefficient;

Including the step of encoding the LFNST index indicating the LFNST kernel used for the LFNST and quantized residual information,

The LFNST is performed based on the LFNST transform set and the LFNST included in the LFNST transform set,

A video encoding method, characterized in that the first bin and the second bin of the syntax element bin string for the LFNST index are encoded using a context coding method.
The method of claim 8,

Encoding the LFNST index,

Deriving a value of a syntax element for the LFNST index;

Deriving context information of a syntax element for the LFNST index;

And encoding bins of a syntax element bin string for the LFNST index based on the context information.
The method of claim 9,

If the tree type of the current block is a single tree, the first bin is derived as first context information,

When the tree type of the current block is not a single tree, the first bin is derived as second context information.
The method of claim 10,

Regardless of the tree type of the current block, context information for the second bin is derived with the same value.
The method of claim 9,

The LFNST transform set includes two LFNST kernels,

The value of the syntax element is 0 indicating a case in which the LFNST is not applied to the current block, 1 indicating a first LFNST kernel among the LFNST kernels, and 2 indicating a second LFNST kernel among the LFNST kernels. Video encoding method comprising one.
The method of claim 12,

The value for the syntax element is binarized into a truncated binary code,

A value of 0 for the syntax element is binarized to '0', a value of 1 for the syntax element is '10', and a value of 2 for the syntax element is binarized to '11'.
A computer-readable digital storage medium in which instruction information causing to perform an image decoding method is stored, the image decoding method comprising:

Deriving a transform coefficient for the current block based on residual information for the current block;

Deriving a modified transform coefficient by applying LFNST to the transform coefficient;

Deriving residual samples for the current block based on the inverse linear transform of the modified transform coefficients; And

Including the step of generating a reconstructed picture based on the residual samples,

The LFNST is performed based on an LFNST transform set, an LFNST kernel included in the LFNST transform set, and an LFNST index indicating the LFNST kernel,

A digital storage medium, characterized in that the first bin and the second bin of the syntax element bin string for the LFNST index are decoded using a context coding method.