RU2623905C1 - Video decoding method - Google Patents

Abstract

FIELD: physics.

SUBSTANCE: video decoding method includes: obtaining the difference samples of the current block and the reference image index; obtaining the spatial vector-candidate for moving in the neighbouring block in the space relative to the current block; ranging the related image corresponding to the temporary vector-candidate for moving the current block, based on the reference image index; obtaining the temporary vector-candidate for moving in the associated block. The associated block is included in the associated image; generate a list of candidate move vectors containing the spatial vector displacement and temporary candidate vector displacement; definition of a motion vector predictor from a list of vectors-candidates move and index of the current block candidate, candidate index indicates one of the vectors move candidates contained in the list of candidate vector displacement; obtaining samples of the current block prediction using motion vector predictor; the current block and reverse engineering using samples of predictions and differential current block samples.

EFFECT: efficient video decoding.

6 cl, 8 dwg, 1 tbl

Description

This application is isolated from application No. 2014119545 for the grant of a patent of the Russian Federation for an invention filed November 8, 2012, with claiming priority on the filing date of the first applications KR 10-2011-0116126 and KR 10-2012-0125799 filed with the Korean Patent Office on 11/08/2011 and 11/08/2012, respectively.

FIELD OF THE INVENTION

The present invention relates to encoding and decoding video data, and more particularly, to a method for decoding a video signal.

State of the art

Recently, there has been an increasing demand in various industries for the use of high-resolution and high-quality video data, such as high-definition (HD; high-definition) and ultra-high-definition (HD) video. As the resolution and quality of the video data increase, so does the amount of data relative to the currently existing conventional video data. Accordingly, when transmitting video data using, for example, current wired and wireless broadband communication lines or storing video data on currently existing storage media, the cost of transmitting and storing video data increases. To solve these problems that arise when increasing the resolution and quality of video data, highly effective methods of compressing video data can be used.

The video data compression method comprises various methods, such as an inter-frame prediction method for predicting pixel values contained in a current image based on previous or subsequent images relative to a current image, an intra-frame prediction method for predicting pixel values in a current image using pixel information in the current image and method for entropy coding by assigning a short code to a value with a high occurrence and assignment frequency for nnogo code value with a low frequency of appearance. Video data can be efficiently compressed and transmitted or stored using such video compression methods.

Disclosure of invention

An object of an aspect of the present invention is to provide a method for decoding a video signal to improve the decoding efficiency of a video signal.

In an embodiment of the present invention, there is provided a method for decoding a video signal. The method includes obtaining differential samples of the current block and the index of the reference image; obtaining a spatial vector of a candidate for moving along a block neighboring in space relative to the current block; selecting a related image related to a temporary candidate motion vector of the current block based on the index of the reference image; obtaining a temporary candidate vector for moving the current block along the linked block, while the linked block is included in the linked image; generating a list of motion candidate vectors comprising a spatial motion candidate vector and a temporal motion candidate vector; determining a motion vector predictor based on the list of motion candidate vectors and the candidate index of the current block, wherein the candidate index indicates one of the motion candidate vectors contained in the list of motion candidate vectors; obtaining prediction patterns of the current block using a motion vector predictor; and reconstructing the current block using prediction patterns and differential samples of the current block.

In such a method, the linked image may have a time order different from the current image containing the current block.

A linked block may be a block corresponding to the same position as the current block.

A block neighboring in space may include at least one of a number of a left neighboring block and an upper neighboring block.

The plurality of displacement candidate vectors in the list of displacement candidate vectors may be arranged in priority order.

The plurality of displacement candidate vectors may be arranged in an order corresponding to the spatial displacement candidate vector and the temporary displacement candidate vector.

Technical result

In accordance with the present invention, a video decoding method improves the decoding efficiency of a video image.

Brief Description of the Drawings

In FIG. 1 is a functional diagram of a video encoding apparatus in accordance with an exemplary embodiment of the present invention.

In FIG. 2 is a functional diagram of a video decoding apparatus in accordance with an exemplary embodiment of the present invention.

In FIG. 3 schematically shows a coefficient scanning method in accordance with the present invention.

In FIG. 4 shows a method for determining and encoding a scanning method based on a division mode of a prediction block in accordance with an exemplary embodiment of the present invention.

In FIG. 5 shows a method for determining and encoding an asymmetric motion partition (AMP) scanning method in accordance with an exemplary embodiment of the present invention.

In FIG. 6 shows a method for determining and encoding a scanning method for short distance intra prediction (SDIP) in accordance with an exemplary embodiment of the present invention.

In FIG. 7 shows a generalized diagram of a video encoding operation in accordance with the present invention.

In FIG. 8 shows a generalized diagram of a video decoding operation in accordance with the present invention.

The implementation of the invention

The present invention may be modified or modified in various ways, and may be illustrated with reference to various examples of embodiments, some of which will be described and shown in the drawings. However, these embodiments are not intended to limit the invention, but are intended to include all modifications, analogs, and substitutions consistent with the spirit and scope of the invention. The same reference numerals in the drawings refer to the same elements throughout the document.

Although the terms “first”, “second”, etc. may be used. to describe various elements, these elements should not be limited to these terms. These terms are used only to distinguish one element from another element. For example, the first element may be called the second element, and the second element may likewise be called the first element without departing from the spirit of the present invention. The term “and / or” includes all and any combination of a plurality of relevant listed elements.

It should be understood that when an element is described as “connected to” or “connected to” by another element, such an element can be directly connected or connected to another element or intermediate elements. On the other hand, when an element is described as “directly connected to” or “directly connected to” another element, there are no intermediate elements.

The terminology used herein is used only to describe particular embodiments and is not intended to limit the invention. As used herein, the singular forms also include the plural unless the context clearly indicates otherwise. It is also clear that the terms “comprises,” “includes,” and / or “has,” as used herein, indicate the presence of the indicated features, entire systems, steps, operations, elements, and / or other components, but do not impede the presence or addition of one or more other features, entire systems, steps, operations, elements, components and / or their associations.

Hereinafter, exemplary embodiments of the invention will be described in detail with reference to the accompanying drawings. The same reference signs in the drawings refer to like elements throughout the document, and redundant descriptions of like elements will be omitted here.

In FIG. 1 is a functional diagram of a video encoding apparatus in accordance with an exemplary embodiment of the present invention.

As shown in FIG. 1, the video encoding apparatus 100 comprises an image division module 110, prediction modules 120 and 125, a transform module 130, a quantization (quantization) module 135, a reordering module 160, an entropy encoding module 165, a de-quantization module 140, an inverse transform module 145, a filtering module 150 and memory (storage device) 155.

Although, for the purpose of explaining various distinctive functions of the video encoding apparatus, the elements in FIG. 1 are shown independently, this configuration does not mean that each element is a separate hardware component or software component. In other words, the elements are shown independent for convenience of description; while to perform functions two or more elements can be combined into one element, or one element can be divided into several elements. Embodiments of the invention in which some elements are combined into one constituent element and / or the element is divided into several independent elements are included in the scope of protection of the present invention without going beyond the essence of the present invention.

Some elements are not necessary for the basic functions of the invention and may be optional components only to improve performance. The invention can be implemented by including only the components necessary for an embodiment of the invention, with the exception of components used only to improve performance. A structure that includes only the necessary components, with the exception of the optical components used only to improve performance, is included in the scope of protection of the invention.

The image dividing unit 110 may split the input image into at least one processing unit. The processing unit may be a prediction unit (PU), a transform unit (transform unit, TU), or a coding unit (coding unit, CU). The image dividing unit 110 may divide a single image into a plurality of combinations of blocks CU, PU and TU and select one combination of CU, PU and TU based on a predetermined criterion (eg, cost function), thereby encoding the image.

For example, one image can be divided into several CUs. A recursive tree structure, such as a quadrant tree structure, can be used to divide an image into CU blocks. A CU for which an image or maximum size CU can be root can be divided into coding subunits with the same number of child nodes as the shared CUs. A CU, which is no longer split according to a predetermined restriction, is a leaf (end) node. In other words, provided that the CU can only be divided into quadrants, a single CU can be divided at most into four different CUs.

In embodiments of the invention, the CU may be used to refer not only to a block for encoding, but also to a block for decoding.

The PU can be divided into at least one square or rectangular shape with the same size as the CU. The shape of PUs isolated from the same CU may differ from each other.

When generating PUs for intra-frame prediction based on the CU and provided that the CU is not a minimum CU, CUs can undergo intra-frame prediction without dividing by several PL) (N × N).

Prediction modules 120 and 125 may include an inter prediction module 120 for performing inter prediction and an intra prediction module 125 for performing intra prediction. Prediction modules 120 and 125 may determine which of the predictions, inter-frame or intra-frame, should be performed for the PU, and may determine characteristic information (e.g., intra-frame prediction mode, displacement vector, and reference image) of the thus determined prediction method. In this case, the processing unit for which the prediction is performed may be different from the processing unit for which the prediction method and characteristic information are determined. For example, a prediction method and a prediction mode may be defined for each PU, while prediction may be performed for each TU. A difference value (difference block) between the generated predicted block and the original block may be input to the conversion unit 130. In addition, information about the prediction mode, information about the displacement vector and the like used for prediction can be encoded together with the difference value by the entropy encoding unit 165 and transmitted to the decoding device. Using a particular encoding mode, the original block can be encoded and transmitted to the decoding device without generating a prediction block by prediction modules 120 and 125.

Inter prediction unit 120 may predict the PU based on the information of at least one image from among the image preceding the current image and the image following the current image. Inter prediction module 120 may include a reference image interpolation module, a motion prediction module, and a motion compensation module.

The reference image interpolation module may receive reference image information from the memory 155 and generate pixel information less than a whole pixel from the reference image. For pixels of the luminance channel, an 8-element discrete cosine transform (DCT) interpolation filter with a variable filter coefficient can be used to generate pixel information less than a whole pixel in 1/4 pixel elements. In the case of color channel pixels, a 4-element discrete cosine transform (DCT) filter with a variable filter coefficient can be used to generate pixel information less than a whole pixel in 1/8 pixel elements.

The motion prediction module may perform motion prediction based on a reference image interpolated by the reference image interpolation module. Various approaches can be used to calculate the displacement vector, such as the full search-based block matching algorithm (FBMA), the three-step search algorithm (TSS), and the new three-step search algorithm (new three -step search, NTS). The displacement vector has the displacement vector value in 1/2 or 1/4 pixel elements based on the interpolated pixel. The motion prediction module may predict the current PU using various motion prediction methods. Various methods can be used as the motion prediction method, such as skip mode, merge mode, and advanced motion vector prediction (AMVP), etc.

Intra-frame prediction unit 125 may generate a PU based on information about a reference pixel adjacent to the current block. The reference pixel information adjacent to the current block is the pixel information in the current image. If the reference pixel is a pixel for which inter prediction is performed, since a block that includes a reference pixel adjacent to the current PU is a block for which inter prediction is performed, information about the reference pixel included in a block for which inter prediction is performed can be replaced by information about the reference pixel in the block for which intra-frame prediction is performed. In other words, if the reference pixel is unavailable, information about the inaccessible pixel may be replaced by information about at least one reference pixel from among the available reference pixels.

The prediction mode for intra-frame prediction includes a directional prediction mode that uses reference pixel information in accordance with a prediction direction and an omnidirectional prediction mode in which direction information is not used to perform prediction. The mode for predicting luminance channel information and the mode for predicting color channel information may be different from each other. In addition, intra-prediction mode information used to obtain luminance channel information or predicted luminance channel signal information can be used to predict color channel information.

If the PUs and TUs are the same size when performing intra-frame prediction, intra-frame prediction for the PU can be performed based on the left pixels, the upper left pixel, and the upper pixels of the PU. On the other hand, if the PUs and TUs have different sizes when performing intra-frame prediction, intra-frame prediction can be performed using reference pixels based on the TU. Intra-frame prediction using NxN division can only be performed for the minimum CU.

In the intraframe prediction method, the predicted block may be generated in accordance with the prediction mode after applying an adaptive intra smoothing (AIS) filter. Different types of AIS filters can be applied to reference pixels. In the intra prediction method, the intra prediction mode of the current PU can be predicted from the intra prediction mode of the PU adjacent to the current PU. When predicting a prediction mode for the current PU using the mode information predicted by the neighboring PU, when the current PU and the neighboring PU have the same intra prediction mode, information indicating that the current PU and the neighboring PU have the same prediction mode can be transmitted using predefined flag information. If the current PU and the neighboring PU have different prediction modes, the prediction mode information for the current block can be encoded by entropy encoding.

A difference block may be generated containing difference information representing the difference between the original PU and the predicted PU generated based on the PU generated by the prediction units 120 and 125. The generated difference block may be transmitted to the conversion module 130.

The transform unit 130 may transform the difference block using a transform method such as Discrete Cosine Transform (DCT) or Discrete Sine Transform (DST). The difference block contains information about the difference between the PU generated by the prediction units 120 and 125 and the original block. The conversion method to be used for transforming the difference block may be selected among DCT and DST based on the intra prediction mode information applied to the PU that was used to generate the difference block.

The quantization (quantization) module 135 may quantize the values converted to the frequency domain by the transform module 130. The quantization coefficient may vary in accordance with a particular block or image significance. Values downloaded from the quantization module 135 may be transmitted to the de-quantization module 140 and the reordering module 160.

The reordering unit 160 may reorder the coefficients in accordance with the quantized difference values.

The reordering unit 160 may change a two-dimensional (2D) block of coefficients into a one-dimensional (1B) coefficient vector by scanning the coefficients. For example, reordering module 125 can change a two-dimensional block of coefficients into a one-dimensional coefficient vector by scanning from DC coefficients to high-frequency coefficients using zigzag scanning. Instead of zigzag scanning, vertical scanning can be used to scan a two-dimensional block of coefficients in the vertical direction and horizontal scanning to scan a two-dimensional block of coefficients in the horizontal direction depending on the size of the TU and the intra prediction mode. In other words, the scanning method used can be selected based on the TU size and the intra prediction mode among zigzag scanning, vertical scanning and horizontal scanning.

Entropy encoding unit 165 may perform entropy encoding based on values obtained by reordering unit 160. Various encoding methods can be used for entropy coding, such as exponential Golomb coding, context-adaptive variable length coding (CAVLC), or context-adaptive binary arithmetic coding, CABAC).

Entropy encoding unit 165 may encode a variety of information, such as difference coefficient information or block type information for CU, prediction mode information, division unit information, PU information, transmission unit information, displacement vector information, reference information frame, information about the interpolation unit and filtering information from the reordering unit 160 and the prediction units 120 and 125.

Entropy coding unit 165 may perform entropy coding of CU coefficients inputted from reordering unit 160.

The de-quantization unit 140 and the inverse transform unit 145 dequantize the values that are quantized by the quantization unit 135 and inverse transform the values transformed by the transform unit 130. The difference values generated by the de-quantization unit 140 and the inverse transform unit 145 may be added to the predicted PU. The predicted PU can be predicted by the motion vector prediction module, the motion compensation module, and the intra-frame prediction module of the prediction modules 120 and 125. The reconstructed block can be generated by adding difference values to the predicted PU (predicted values).

Filtering module 150 may comprise at least one of a deblocking filter, an offset module, and an adaptive loop filter (ALF).

The deblocking filter can remove block distortions generated at the boundaries between blocks in the reconstructed image. The decision to apply a deblocking filter to the current block can be made based on the pixels contained in several rows or columns of the block. If a block suppression filter is applied to the block, a strong filter or a weak filter may be applied depending on the desired block suppression filtering intensity. When performing horizontal filtering and vertical filtering using a deblocking filter, horizontal filtering and vertical filtering can be performed in parallel.

The offset module may apply the offset from the original image in units of pixel to the image for which the deblocking operation is completed. The area to which the offset can be applied can be determined after dividing the image pixels by a predetermined number of areas. The offset can be applied to the area defined in this way, taking into account the information about the boundaries of each pixel and the method of applying the offset to a specific area.

ALF may perform filtering based on a comparison of the filtered filtering of the reconstructed image and the original image. The pixels contained in the image can be divided into predefined groups, the filter applied to each group can be determined, and differential filtering can be performed for each group. Information about whether to use ALF may be transmitted for each coding unit (CU), and the size and coefficient of the applied ALF may vary for each block. ALF can be of several types, and the number of coefficients contained in the corresponding filter may vary. In addition, an ALF filter of the same shape (fixed shape) can be applied to a block regardless of the properties of the block.

A memory (storage device) 155 may store the reconstructed block or image output by the filtering unit 150, and the stored reconstructed block or image may be provided to the prediction units 120 and 125 when performing inter-frame prediction.

In FIG. 2 is a functional diagram of a video decoding apparatus in accordance with an exemplary embodiment of the present invention.

As shown in FIG. 2, the video decoding apparatus 200 may include an entropy decoding module 210, a reordering module 215, a de-quantization (de-quantization) module 220, an inverse transform module 225, a prediction module 230 and 235, a filter module 240, and a memory 245.

Upon receipt of the video bitstream from the video encoding device, the input bit stream may be decoded in accordance with the operation inverse to the video encoding operation performed in the video encoding device.

Entropy decoding unit 210 may perform entropy decoding in accordance with an operation inverse to the entropy encoding operation by the entropy encoding unit of the video encoding apparatus. For example, various methods could be used for entropy encoding, such as the Golomb exponential code, CAVLC or SAVAC in accordance with the method used by the video encoding device.

Entropy decoding unit 210 may decode information related to inter prediction and intra prediction performed by the encoding device.

The reordering unit 215 may reorder the entropy decoding bitstream in the entropy decoding unit 210 based on the method of reordering the encoding unit. The reordering module 215 can reconstruct and reorder the coefficients in the form of a one-dimensional vector into coefficients in a two-dimensional block. The reordering module 215 may obtain coefficient scanning information performed by the encoding device, and may reorder using the coefficient inverse scanning method based on the scanning order in which the scanning was performed by the encoding device.

The dequantization module 220 is configured to dequantize based on a quantization parameter obtained from an encoding device and reordered block coefficients.

The inverse transform module 225 may perform the inverse DCT and inverse DST of a quantization result performed by the video encoding apparatus subjected to DCT and DST in the transform module. Inverse transformation can be performed based on the transmission unit determined by the video encoding device. The video encoding device transform module may selectively perform DCT and DST depending on a plurality of information elements, such as a prediction method, current block size and prediction direction, etc., and the video decoding apparatus inverse transform module 225 may perform the inverse transform based on the information about the conversion performed by the conversion module of the video encoding device.

Prediction modules 230 and 235 may generate a prediction block (predicted block) based on information on generating a prediction block received from entropy decoding module 210 and information on a previously decoded block or image received from memory 245.

Similar to the operation of the video encoding device as described above, if the PU and TU are the same size when performing intra-frame prediction, intra-frame prediction for the PU is performed based on the left pixels, the upper left pixel and the upper pixels of the PU. On the other hand, if the PUs and TUs have different sizes when performing intra-frame prediction, intra-frame prediction can be performed using reference pixels based on the TU. Intraframe prediction using NxN division can only be used for minimum CU.

Prediction modules 230 and 235 may include a PU determination module, an inter prediction module, and an intra prediction module. The PU determination module may receive various information such as information about the PU, information about the prediction mode of the intra-frame prediction method, and information related to prediction of the movement of the inter-frame prediction method, etc. from entropy decoding unit 210, and determining a PU for the current CU. The PU determination module may determine whether to perform inter-frame or intra-frame prediction for the PU. Inter prediction unit 230 may perform inter prediction for the current PU based on the information of at least one image from a previous image and a subsequent image relative to the current image including the current PU. Inter prediction unit 230 may use the information necessary for inter prediction for the current PU obtained from the video encoding device.

To perform inter-frame prediction based on the CU, it can be determined whether the motion prediction method for the PU contained in the CU is a skip mode, a merge mode, or an AMVP mode.

Intra-frame prediction unit 235 may generate a prediction block based on pixel information in the current image. If the PU is a PU for which intra prediction is performed, intra prediction can be performed based on the intra prediction mode information for the PU received from the video encoding apparatus. The intra prediction module 235 may include an AIS filter, a reference pixel interpolation module, and a DC filter. The AIS filter filters the reference pixels of the current block. The AIS filter may decide to apply the filter depending on the prediction mode for the current PU. AIS filtering can be performed for the reference pixels of the current block using the prediction mode for the PU and AIS filter information received from the video encoding device. If the prediction mode for the current block is a mode where AIS filtering is not applied, the AIS filter may not be applied.

If the prediction mode for the PU is a prediction mode with intra-frame prediction based on pixel values obtained by interpolating the reference pixels, the reference pixel interpolation module can generate reference pixels in units of fractional pixels smaller than the whole pixel (i.e., full pixel) by interpolating the reference pixels. If the prediction mode of the current PU is a prediction mode with the generation of a prediction block without interpolating the reference pixels, the reference pixels may not be interpolated. The DC filter may generate a prediction block by filtering if the prediction mode for the current block is a DC mode.

The reconstructed block or image may be transmitted to the filtering module 240. Filter module 240 includes a deblocking filter, an offset module, and an ALF.

The video encoding apparatus may provide information on whether a deblocking filter is applied to the corresponding block or image, and information on applying a strong filter or weak filter when using a deblocking filter. Information about the blocking filter can be transmitted to the block suppression filter of the video encoding apparatus from the video encoding apparatus, and it can perform block suppression filtering with respect to the corresponding block.

The offset module may apply the offset to the reconstructed image based on the type of offset and the offset value applied to the image during the encoding operation.

ALF can be applied to the CU based on ALF application information, ALF coefficient information, etc., received from the encoding device. ALF information can be included and transmitted in a separate set of parameters.

The memory 245 may store the reconstructed image or block for use as a reference image or reference block, and transmit the reconstructed image to an output module.

As described above, in embodiments of the invention, the term “coding unit” is used for a coding unit for convenience of description. However, the term “coding block” can also be used for a block for decoding.

Further in FIG. 3-8, scanning methods based on prediction modes and division modes in accordance with exemplary embodiments of the present invention, implemented in accordance with the functions of the modules of the encoding device and the decoding device described above in FIG. 1 and 2, which fall within the protection scope of the present invention.

In FIG. 3 schematically shows coefficient scanning methods in accordance with the present invention.

As shown in FIG. 3, scanning methods may include horizontal scanning 310, vertical scanning 320, zigzag scanning 330, or vertical-diagonal scanning 340. In this case, one of these scanning methods shown in FIG. 3 can be used based on the division form of the PU, and the two-dimensional block of quantized transform coefficients can be replaced by a one-dimensional vector of transform coefficients by scanning.

A horizontal scan 310 scanning the transform coefficients in the horizontal direction can be applied, for example, if the PU is a division, which is a vertically oriented block, such as an N × 2N block. A vertically oriented block with a high probability includes the texture of the vertical component, where the conversion coefficients are most likely distributed in the horizontal direction. Thus, the scan order shown in method 310 of FIG. 3 can be applied to scanning conversion coefficients.

A vertical scan 320 scanning vertical transform coefficients can be applied, for example, if the PU is a division that is a horizontally oriented block, such as a 2N × N block. A horizontally oriented block most likely includes the texture of the horizontal component, in which the conversion coefficients are most likely distributed in the vertical direction. Thus, the scan order shown in method 320 of FIG. 3 can be applied to scanning conversion coefficients.

A zigzag scan 330 or a vertical-diagonal scan 340 can be applied if the PU does not have a pronounced anisotropy (directivity) or a specific texture component. For example, a zigzag scan 330 or a vertical diagonal scan 340 can be applied to a 2N × 2N or N × N square block.

In FIG. 3, scanning methods are shown as exemplary embodiments of the present invention, and the present invention is not limited to them. Alternative scanning methods performed in a different order can also be used along with the scanning methods in FIG. 3.

As described above, if the PU is a division, such as an N × 2N block or a 2N × N block, these blocks are likely to have a specific texture component or strong anisotropy. Accordingly, depending on the division form of the PU, horizontal scanning or vertical scanning is used. However, despite the fact that the PU is a division, such as an N × 2N block or a 2N × N block, these blocks may have slight anisotropy or not contain a specific texture component. In this case, the use of certain scanning methods, for example, horizontal scanning of an N × 2N block and vertical scanning of a 2N × N block, may not be effective. Thus, a method for efficiently scanning and coding transform coefficients is required.

In FIG. 4 shows a method for determining a scanning method and encoding information about it based on the division mode of the PU in accordance with an exemplary embodiment of the present invention.

As shown in FIG. 4, a single CU in inter prediction mode can be divided into PUs of the same size or different sizes. For example, the CU may be divided into a 2N × N block 400, an N × 2N block 410, a 2N × 2N block 420, or an N × N block 430. PartMode PU division modes can be determined based on the size of the divided PUs.

PartMode PU division modes may include a PART_2N × N mode in which CUs are divided into 400 2N × N blocks, a PART_N × 2N mode in which CUs are divided into N × 2N blocks 410, a PART_2N × 2N mode in which CUs are divided into 420 blocks 2N × 2N and the PART_N × N mode in which CUs are divided into 430 N × N blocks.

In the present embodiment, the scanning method is determined based on the division mode of the PU, in which the division form of the division mode can be taken into account. In other words, possible scanning methods can be obtained taking into account the division forms of the PU blocks, among which the scanning method can be determined based on the RDO.

If the division mode indicates a horizontally oriented shape, for example, the division mode is PART_2N × N mode, in which the CU is divided into 400 2N × N blocks, the blocks are likely to contain a specific texture component or have anisotropy (for example, a horizontal texture component or transform coefficients distributed in the vertical direction). As a possible scanning method, vertical scanning can be determined taking into account this form of division. Also, as a possible scanning method, zigzag scanning (or vertical-diagonal scanning) can be determined, given that the blocks are likely to not contain a specific texture component or to have anisotropy. In other words, for the division mode of a horizontally oriented shape from two possible scanning methods, namely, vertical scanning and zigzag scanning (or vertical-diagonal scanning), a scanning method having a minimum RDO can be selected.

At the same time, if the division mode indicates a vertically oriented shape, for example, the division mode is PART_N × 2N mode, in which the CU is divided into 410 N × 2N blocks, the blocks are likely to contain a certain texture component or have anisotropy (for example, vertical texture component or transform coefficients distributed in the horizontal direction). As a possible scanning method, horizontal scanning can be determined taking into account this form of division. Also, as a possible scanning method, zigzag scanning (or vertical-diagonal scanning) can be determined, given that the blocks are likely to not contain a specific texture component or to have anisotropy. In other words, for the division mode of a vertically oriented shape from two possible scanning methods, namely, horizontal scanning and zigzag scanning (or vertical-diagonal scanning), a scanning method having a minimum RDO can be selected.

Meanwhile, for the square division mode, for example, the PART_2N × 2N mode in which the CU is divided into blocks 2N × 2N, or the PART_N × N mode in which the CU is divided into 430 N × N blocks, zigzag scanning can be used ( or vertical diagonal scan).

Table 1 presents the available scanning methods in accordance with the division modes of the PU in accordance with an exemplary embodiment of the present invention. Here, in the PART_2N × N mode and the PART_N × 2N mode, one scanning method can be selected taking into account the RDO of two possible scanning methods.

When the scanning method is determined based on the division mode of the PU, as described above, the transform coefficients can be scanned using the scanning method so determined. Information about a particular scanning method can be encoded and transmitted to a decoding device. Information about the scanning method can be specified using a flag, for example, the isZigZagScanFlag flag, indicating whether zigzag scanning is used.

For example, when the PU division mode is PART_2N × N mode, information about the scanning method thus determined by vertical scanning and zigzag scanning (or vertical-diagonal scanning) can be encoded using a flag, and flag information can be transmitted to the decoding device. In PART_2N × N mode, the isZigZagScanFlag flag can be set to 1 if zigzag scanning is defined, and the isZigZagScanFlag flag can be set to 0 if vertical scanning is determined. At the same time, if the PU division mode is PART_N × 2N mode, information about the scanning method thus determined by horizontal scanning and zigzag scanning (or vertical-diagonal scanning) can be encoded using a flag, for example, the isZigZagScanFlag flag, and the flag information can be transmit to the decoding device.

In FIG. 5 shows a method for determining a method for scanning and encoding information about it in asymmetric motion partition (AMP) in accordance with an exemplary embodiment of the present invention.

As described above, a single CU in inter prediction mode can be divided into PUs of the same size or different sizes. As shown in FIG. 5, a 64 × 64 block can be divided into a 16 × 64 block, a 48 × 64 block, a 64 × 16 block, or a 64 × 48 block, i.e. blocks of various shapes. This division mode is called AMP. AMP can be applied to CU division to improve coding efficiency if the image contains irregular image structures.

From left to right in FIG. 5 AMP contains PART_nL × 2N mode, in which CU is divided into blocks 500 of size nL × 2N, PART_nR × 2N mode, in which CU is divided into blocks 510 of size nR × 2N, PART_2N × nU mode, in which CU is divided into blocks of 520 size 2N × nU, and the PART_2N × nD mode, in which the CU is divided into blocks 530 of size 2N × nD. Here, in the PART_nL × 2N mode and the PART_nR × 2N mode, the PU may have a size of 501 and 512 1 / 2N × 2N or a size of 502 and 511 3 / 2N × 2N. In the PART_2N × nU and PART_2N × nD mode, the PU can have a size of 521 and 532 2N × 1 / 2N or a size of 522 and 531 2N × 3 / 2N.

As described in FIG. 4, in accordance with an embodiment of the present invention, the scanning method can be determined based on the division mode, in other words, the size of the divided block in the AMP. In other words, possible scanning methods can be obtained taking into account AMP division forms, among which the scanning method can be determined based on the RDO.

For example, for a vertically oriented block (a block whose height is greater than its width) in 1 / 2N × 2N mode, such as the left block 501 of the 500 nL × 2N block and the right block 512 of the block 510 of the nR × 2N block, as possible scanning methods horizontal scanning can be determined taking into account a specific component of the texture or anisotropy that a vertically oriented block may possess (for example, a vertical texture component and transform coefficients distributed in the horizontal direction), or zigzag scanning (or vertical n-diagonal scan), taking into account the fact that a vertically oriented block does not have a specific texture component or anisotropy. In this case, of the two possible scanning methods, a scanning method having a minimum RDO can be selected.

At the same time, for a horizontally oriented block (a block whose width is greater than its height) in the 2N × 1 / 2N mode, such as the upper block 521 of the 520 2N × nU block and the lower block 532 of the 530 2N × nD block Scanning methods can be determined by vertical scanning taking into account a certain component of the texture or anisotropy, which a horizontally oriented block may possess (for example, a horizontal texture or transform coefficients distributed in the vertical direction), or zigzag scanning (or vertically agonal scanning), taking into account the fact that a horizontally oriented block does not have a specific texture component or anisotropy. In this case, of the two possible scanning methods, a scanning method having a minimum RDO can be selected.

Meanwhile, zigzag scanning (or vertical-diagonal scanning) can be used for large divided portions of nL × 2N 500, nR × 2N 510, 2N × nU 520 and 2N × nD 530 (i.e., 3 / 2N × 2N and 2N modes × 3 / 2N). In other words, zigzag scanning (or vertical-diagonal scanning) can be used for right division 502 of the 500 nL × 2N block, left division of 512 block 510 nR × 2N, lower division 522 of block 520 2N × nU and upper division 53 of block 530 2N × nD .

When the scanning method is determined based on the AMP mode, as described above, information about the scanning method thus determined can be encoded. For example, as described above in FIG. 4, in PART_nL × 2N mode and PART_nR × 2N mode and for vertically oriented blocks 501 and 512 (i.e., 1 / 2N × 2N mode), the isZigZagScanFlag flag can be set to 1 if zigzag scanning is used, and the isZigZagScanFlag flag can be set to 0 if horizontal scanning is used. In PART_2N × nU and PART_2N × nD modes and for horizontally oriented blocks 521 and 532 (i.e., 2N × 1 / 2N mode), the isZigZagScanFlag flag can be set to 1 if zigzag scanning is used, and the isZigZagScanFlag flag can be set to 0 if vertical scan is used. This flag information may be encoded and transmitted to a decoding device.

In FIG. 6 shows a method for determining a method for scanning and encoding information about it for short distance intra prediction (SDIP) in accordance with an exemplary embodiment of the present invention.

SDIP relates to a method for dividing a CU into 2N × 2N PUs, N × N PUs, 1 / 2N × 2N PUs, or 2N × 1 / 2N PUs and performing intra-frame prediction for the divided PU. When performing SDIP, the distance between the intra-prediction reference pixel and the target reference pixel can be reduced compared to conventional intra-frame prediction using a square PU. Thus, the difference value, which is the difference value between the original pixel and the predicted target pixel (predicted pixel), is reduced, which leads to an increase in coding efficiency.

As shown in FIG. 6, one CU can be divided into PUs with different sizes depending on image properties. For example, 32 × 32 CUs can be divided into four 16 × 16 PUs 610, 620, 630 and 640. 16 × 16 PU 610 can be further divided into four 4 × 16 PU 611, 612, 613 and 615, of which 4 × 16 PU 611 can be further divided into four PU 611-1, 611-2, 611-3 and 611-4 in size 1 × 16.

In the same way, a 16 × 16 PU 630 can be further divided into four 8 × 8 PUs. PU 631 of size 8 × 8 can be further divided into four PU 631-1, 631-2, 631-3 and 631-4 of size 2 × 8. Also, 8 × 8 PU 632 can be further divided into four 4 × 4 PUs, of which 4 × 4 PU 632-1 can be further divided into four 1 × 4 PUs.

As described above with reference to FIG. 4 and 5, the scanning method is determined based on the division mode of the PU in SDIP, in other words, the size of the PU in the present embodiment. In other words, possible scanning methods are obtained taking into account the division forms of the PU, among which determine the scanning method based on the RDO.

For example, if the PU division mode in SDIP is 1 / 2N × 2N, which has a vertically oriented division form such as 4 × 16 PU 611, 612, 613 and 614, PU 631-1, 631-2, 631-3 and 631-4 2 × 8 in size and 1 × 4 PU, as possible scanning methods, horizontal scanning and zigzag scanning (or vertical-diagonal scanning) can be determined taking into account a specific texture component or anisotropy (for example, vertical texture and conversion factors, distributed in the horizontal direction). In this case, from two possible scanning methods, you can choose a scanning method that has a minimum RDO.

At the same time, if the PU division mode in SDIP is 2N × 1 / 2N having a horizontally oriented division form, such as 16 × 4 PU, 8 × 2 PU and 4 × 1 PU, as possible scanning methods can vertical scanning and zigzag scanning (or vertical-diagonal scanning) are determined taking into account a specific component of the texture or anisotropy (for example, horizontal texture and transform coefficients distributed in the vertical direction). In this case, from two possible scanning methods, you can choose a scanning method that has a minimum RDO.

Information about the scanning method defined in this way can be encoded using a flag, for example, the isZigZagScanFlag flag, and transmitted to the decoding device, as described above in FIG. 4 and 5.

In FIG. 7 shows a generalized diagram of a video encoding method in accordance with the present invention. Each step in FIG. 7 may be performed by the respective modules of the video encoding apparatus of FIG. one.

As shown in FIG. 7, the CU of the current image is input to the encoding device (S700). If the entered CU is an inter prediction mode CU, the inter prediction mode CU (“inter-frame CU”) may comprise a plurality of inter prediction mode PUs (“inter-frame PU”) and have one of two prediction modes (PreMode), a skip mode (“MODE_SKIP” ") And inter-frame mode (" MODE_INTER ").

CUs in MODE_SKIP mode are no longer divided into smaller PUs, and movement information about the PUs in the PartMode division mode in PART_2N × 2N is placed for it.

A CU in MODE_INTER mode can be divided into four types of PUs, in which information about the prediction mode is the MODE_NTER mode (PredMode == MODE_INTER) and information about which of The division modes PART_2N × 2N, PART_2N × N, PART_N × 2N and PART_N × N are used (i.e. the information that PartMode == PART_2N × 2N, PartMode == PART_2N × N, PartMode == PART_N × 2N or PartMode == PART_N × N).

The encoding device performs motion prediction for the current inter-frame PU (S710). When the CU is divided into a plurality of PUs, the currently encoded PU (“current PU”) is introduced. The encoding device may perform motion prediction for the current PU using the previous frame, subsequent frame, or previous and subsequent frames with respect to the current frame. Motion information for the current PU, such as a motion vector, a reference image index, and a prediction direction index, can be obtained by moving prediction.

The encoding device may determine the value of the motion prediction of the current PU in the inter prediction mode (S720). The moving information for the current PU is not transmitted to the decoding device in an unchanged form, however, the difference values from the predicted values received from neighboring blocks in time and space are transmitted to the decoding device to increase the compression efficiency. A motion prediction method may include a merge mode and an AMVP mode, which can be used to determine a motion prediction value.

In merge mode, merge candidates are obtained based on information about the movement of blocks adjacent to the current PU in time and space. If there is a candidate among the candidates having the same movement information as the current PU, the encoding device may send a Merge_Flag flag indicating the use of the merge mode and an index of the candidate having the same moving information as the current PU to the decoding device . Specifically, the encoding device determines the value of the available motion vector predictor (MVP) using the refldxLX index of the reference image indicating the reference image obtained from the motion prediction, and creates a list of merge candidates (MergeCandList). If there is a candidate in the list that has the same movement information as the current PU, the encoder sets the Merge_Flag flag to 1 and encodes the candidate's Merge_Idx index.

In AMVP mode, the encoding device determines AMVP candidates based on movement information for blocks adjacent to the current PU in time and space. In other words, the encoding device determines the mvpLX displacement vector predictor value for the luminance channel component. Specifically, the encoding device determines spatial candidate motion vectors (MVPs) of neighboring PUs for the current PU. The encoding device determines a temporary candidate motion vector of the associated block using the RefldxLX index of the reference image obtained from the motion prediction. The encoding device creates the MVP list mvpListLX based on the spatial displacement candidate vectors and the temporary displacement candidate vector. If most motion vectors have the same value in the MVP list, the encoder removes the motion vectors other than the motion vector that has the highest priority from the MVP list. In this case, the movement vectors may have priority in the order of the vectors (mvLXA) of moving the left neighboring blocks with the current PU, the vectors (mvLXB) of moving the upper neighboring blocks with the current PU, and the moving vector (mvLXCol) of the temporary linked block, which are available. From the MVP list, the best predictor displacement vector is selected among the displacement candidate vectors as the predicted mvpLX value. The best predictor is a candidate block that minimizes the cost function of the relationship between speed and distortion (rate-distortion, RD), for example, J _MotSAD , taking into account the cost of transmitting a bit and the sum of absolute difference (SAD).

The encoding device encodes movement information for the current PU (S730). When the merge mode is used to predict the movement of the current PU, if the candidate having the same movement information as the current PU is present among the merge candidates, the encoding device indicates that the merge mode is applied to the current PU, and encodes and transmits a flag Merge_Flag indicating the use of the merge mode, and the Merge_ldx index of the candidate having the same move information as the current PU to the decoding device.

If AMVP mode is used to predict the movement of the current PU, the encoding device determines the candidate minimizing the cost function among the AMVP candidates by comparing the information of the candidate movement vector of the AMVP with the information of the moving vector of the current PU. The encoding device performs motion compensation using a candidate minimizing the cost function and a difference value between the information of the movement of the candidate minimizing the cost function and the moving information of the current PU, thereby obtaining a difference signal. In other words, the encoding device can perform entropy encoding of the difference between the motion vector of the current PU and the motion vector of the best predictor.

The encoding device receives a difference signal by determining a difference in pixels between the pixel value of the current block and the pixel value of the prediction block by displacement compensation (S740) and converts the difference signal (S750).

The difference signal is encoded by a transform in which a transcoding core can be used for the transform. The transcoding core can be in the form of 2 × 2, 4 × 4, 8 × 8, 16 × 16, 32 × 32 or 64 × 64, while the core used for the conversion can be determined in advance. In this case, the conversion coefficients are generated by the conversion and form a two-dimensional block. For example, conversion coefficients C for an n × n block can be derived using formula 1.

In this case, C (n, n) is the n × n matrix of transform coefficients, T (n, n) is the n × n matrix of the transform kernel, and B (n, n) is the n × n matrix of the difference block.

The conversion coefficients calculated by formula 1 are quantized.

Based on the RDO, the encoding device determines what exactly to transmit: a difference signal or conversion coefficients (S760). If the prediction is performed properly, the difference signal can be transmitted unchanged, without transcoding. In this case, the encoding device can compare the cost functions before / after transcoding and choose a method with a minimum cost.

The encoding device may transmit the type of signal to be transmitted (for example, a differential signal or transform coefficients) with respect to the current block and transmit the signal to the decoding device. For example, if transmitting the difference signal unchanged without transcoding has a minimum cost, the encoding device may transmit the difference signal with respect to the current block. If the transmission of transform coefficients is at a minimum cost, the encoding device may transmit transform coefficients with respect to the current block.

The encoding device scans the conversion coefficients (S770). The coding device by scanning converts the quantized transform coefficients of the shape of a two-dimensional block into the transform coefficients of the shape of a one-dimensional vector. In this case, based on the size of the PU, in other words, the division mode of the PU, horizontal scanning, vertical scanning, and zigzag scanning (or vertical-diagonal scanning) can be selected for scanning conversion coefficients.

Specifically, based on the division forms of the PU, possible scanning modes (methods) can be determined, among which the scanning mode is determined based on the RDO. If the division mode of the PU has a vertically oriented division form, horizontal scanning and zigzag scanning (or vertical-diagonal scanning) are determined as possible scanning modes. If the division mode of the PU has a horizontally oriented division form, vertical scanning and zigzag scanning (or vertical-diagonal scanning) are determined as possible scanning modes. Then, from the possible scan modes, a scan mode with a minimum RDO is selected.

In this case, as described above in FIG. 4 and 6, such scanning modes can be applied to PU division modes in inter-frame prediction, for example, N × 2N block, 2N × N block, 2N × 2N block, N × N block, 2N × nU block, 2N × nD block , an nL × 2N block and an nR × 2N block, and PU division modes in the intra prediction mode (for example, SDIP), for example, the modes of a 1 / 2N × 2N block, a 2N × 1 / 2N block, an N × N block, and a 2N × 2N block . In this regard, the relevant descriptions are omitted, since they have already been given in full.

The encoding device may perform entropy encoding of the transmitted information (S780). In other words, the encoding device can entropy encode the scanned transform coefficients and the prediction mode information. The encoded information can form a compressed bitstream and is stored or transmitted through an abstract network layer (network abstraction layer, NAL).

In FIG. 8 shows a generalized diagram of a method for decoding video data in accordance with the present invention. Each step in FIG. 8 can be performed by the respective modules of the video decoding device in FIG. 2.

As shown in FIG. 8, a decoding apparatus may perform entropy decoding of a received bitstream (S800). The decoding device can identify the block type from the variable length coding (VLC) table to recognize the prediction mode of the current block. Additionally, the encoding device can identify information about whether the transmitted information about the current block is a difference signal or conversion coefficients. Depending on the result, the decoding device may receive a difference signal or transform coefficients for the current block.

The decoding device may determine a scanning method (S810). In other words, the decoding apparatus determines a scanning method based on the division mode of the PU using information transmitted from the encoding apparatus. The information transmitted may be a flag indicating whether zigzag scanning is used (for example, the isZigZagScanFlag flag).

Specifically, if the division mode of the PU has a vertically oriented division form or a horizontally oriented division form, the decoding apparatus decodes a flag indicating the use of zigzag scanning and determines a scanning method based on the value of the decoded flag. If the division mode of the PU has a vertically oriented division form, the decoding device selects zigzag scanning or horizontal scanning based on the value of the decoded flag. If the division mode of the PU has a horizontally oriented division form, the decoding device selects zigzag scanning or vertical scanning based on the value of the decoded flag. For example, if the isZigZagScanFlag flag is 1, zigzag scanning is selected, while horizontal scanning (for the division mode having a vertically oriented division shape) / vertical scanning (for the division mode having a horizontally oriented division form) can be used if the isZigZagScanFlag flag is 0 .

In this case, as described above in FIG. 4 and 6, these scanning methods can be applied to inter-prediction PU division modes, for example, N × 2N block, 2N × N block, 2N × 2N block, N × N block, 2N × nU block, 2N × nD block, an nL × 2N block and an nR × 2N block and PU division modes in intra-frame prediction (for example, SDIP), for example, modes of a 1 / 2N × 2N block, 2N × 1 / 2N block, N × N block and 2N × 2N block. In this regard, the relevant descriptions are omitted, since they have already been given in full.

Meanwhile, zigzag scanning can be used for the division mode having a square shape, such as the mode of the 2N × 2N block and the N × N block, or for the right division of the nL × 2N block mode, the left division of the nR × 2N block mode, the lower division mode of the 2N block × nU or upper division block mode 2N × nD as large divisions in the AMP.

The decoding device may reverse scan the entropy decoding of the difference signal or transform coefficients (S820). The decoding device may generate a difference block by means of an inverse scan in the case of a difference signal and may generate a two-dimensional transform block by means of an inverse scan in the case of conversion coefficients. When the transform block is generated, the decoding device can dequantize and inverse transform the transform block, thereby obtaining a difference block. The operation of obtaining a difference block by the inverse transform of the transform block is expressed in formula 2.

In this case, B (n, n) is the n × n matrix of the difference block, T (n, n) is the n × n matrix of the transformation kernel, and C (n, n) is the n × n matrix of transformation coefficients.

A decoding device may perform inter-frame prediction (S830). The decoding apparatus may decode prediction mode information and perform inter-frame prediction in accordance with the prediction mode.

For example, if the prediction mode PredMode is a merge mode (e.g., PredMode == MODE_SKIP && Merge_Flag === 1), the decoding device may determine the luminance channel component moving vector mvLX and the reference image index refldxLX for the merge mode. To this end, the decoding device can determine merge candidates for PU divisions (i.e., prediction blocks) adjacent to the current PU in space. The decoding device may determine the refldxLX index of the reference image so as to obtain a temporary merge candidate for the current PU. The decoding device may determine the value of the available motion vector predictor (MVP) using the thus defined reference image index. If the number of NumMergeCand candidates in the MergeCandList list of merge candidates composed of spatial merge candidates and a temporary merge candidate is 1, the decoding device assigns the merge candidate index (Mergejdx) to 1. Otherwise, the decoding device can assign the merge candidate index equal to the accepted merge index. The decoding device determines a motion vector (mvLX) of the merge candidate indicated by the received merge index and the reference image index (refldxLX). The decoding device may use the motion vector thus defined and the reference image index to compensate for the movement.

If the prediction PredMode mode is AMVP mode, the decoding device may determine the reference image index (refldxLX) for the current PU and may determine the luminance channel component moving vector predictor value (mvpLX) using the reference image index. Specifically, the decoding apparatus may determine spatial motion candidate vectors (MVPs) of neighboring PUs for the current PU and determine a temporal motion candidate vector (MVP) of the associated block, which is indicated by the reference image index. The decoding apparatus may generate an MVP list (mvpListLX) based on the spatial displacement candidate vectors thus determined and the temporary displacement candidate vector. If the plurality of displacement vectors in the MVP list have the same value, the decoding device may remove the displacement vectors other than the displacement vector with the highest priority from the MVP list. In this case, as described above, the movement vectors take precedence in the order of the vector (mvLXA) of the movement of the left neighboring block with the current PU, the vector (mvLXB) of the movement of the upper neighboring block with the current PU and the vector (mvLXCol) of the temporary linked block that are available . If the number of NumMVPCand (LX) MVP candidates in the MVP list is 1, the decoding device can set the MVP candidate mvpldx index to 0. If the number of MVP candidates is 2 or more, the decoding device can set the MVP candidate mvpldx index to the accepted index value. The decoding device may determine the motion vector indicated by mvpldx among the MVP candidates in the MVP list (mvpListLX) as the mvpLX value of the motion vector predictor. The decoding apparatus may determine the mvLX displacement vector using the displacement vector predictor mvpLX value and formula 3.

In this case, mvLX [0], mvdLX [0] and mvpLX [0] are the components x of information about the displacement vector LX (that is, the components x mvLX, mvdLX and mvpLX), a mvLX [1], mvdl_X [1] and mvpLX [1] - components of information about the LX displacement vector (ie components of mvLX, mvdLX and mvpLX).

The decoding device may determine the reconstructed signal (S840). For example, a decoding device may add a difference signal to a signal of a previous frame (i.e., a predicted signal) to generate a reconstructed signal. The decoding device may add a prediction signal of a previous frame, which is obtained by motion compensation using a specific displacement vector, to the decoded difference signal for the current PU, thereby generating a reconstructed signal.

Although the methods have been described as a sequence of steps or blocks based on generalized schemes of the above embodiments, the present invention is not limited to the above sequence of steps. Some steps may be performed in an order different from that described above, or simultaneously. It will also be understood by those skilled in the art that the steps shown in the generalized diagrams are not limiting, and additional steps may be included in the circuit, or one or more steps may be removed from the circuit without affecting the scope of the present invention.

While several exemplary embodiments of the invention have been shown and described with reference to the accompanying drawings, it will be apparent to those skilled in the art that various modifications and variations can be made based on the above descriptions without departing from the gist of the present invention. Exemplary embodiments of the invention are not intended to limit the principle of the present invention, but to illustrate the present invention and not to limit the scope of the present invention. The limits of the essence of the present invention are defined by the attached claims, and all differences within the essence suggest their inclusion in the attached claims of the present invention.

Claims (14)

1. A method of decoding a video signal, including: obtaining differential samples of the current block and the reference image index; obtaining a spatial vector of a candidate for moving along a block neighboring in space relative to the current block; selecting a related image related to a temporary candidate motion vector of the current block based on the index of the reference image; obtaining a temporary candidate vector for moving the current block along the linked block, while the linked block is included in the linked image; generating a list of motion candidate vectors comprising a spatial motion candidate vector and a temporal motion candidate vector; determining a motion vector predictor based on the list of motion candidate vectors and the candidate index of the current block, wherein the candidate index indicates one of the motion candidate vectors contained in the list of motion candidate vectors; obtaining prediction patterns of the current block using a motion vector predictor; and reconstruction of the current block using prediction patterns and difference patterns of the current block. 2. The method according to p. 1, characterized in that the associated image has a temporal order different from the current image containing the current block. 3. The method according to p. 2, characterized in that the associated block represents a block corresponding to the same position as the current block. 4. The method according to p. 1, characterized in that the neighboring space block includes at least one of a number of a left neighboring block and an upper neighboring block. 5. The method according to claim 4, characterized in that the plurality of displacement candidate vectors in the list of displacement candidate vectors are arranged in priority order. 6. The method according to claim 5, characterized in that the plurality of displacement candidate vectors are arranged in the order corresponding to the spatial displacement candidate vector and the temporary displacement candidate vector.

Images