CN106910241A - The reconstructing system and method for the three-dimensional human head based on cell-phone camera and Cloud Server - Google Patents
The reconstructing system and method for the three-dimensional human head based on cell-phone camera and Cloud Server Download PDFInfo
- Publication number
- CN106910241A CN106910241A CN201710040536.XA CN201710040536A CN106910241A CN 106910241 A CN106910241 A CN 106910241A CN 201710040536 A CN201710040536 A CN 201710040536A CN 106910241 A CN106910241 A CN 106910241A
- Authority
- CN
- China
- Prior art keywords
- threedimensional model
- cloud server
- point
- picture
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of three-dimensional number of people reconstructing system based on cell-phone camera and Cloud Server and method, (1) generates characteristic point by image procossing.(2) every image position relationship in three dimensions is constructed by the contrast of characteristic point, matching.(3) based on each picture feature point and position relationship, threedimensional model is tentatively generated.(4) by recovering the illumination condition of threedimensional model, the geometrical model with confidence level high is further recovered.Beneficial effects of the present invention are as follows：The photo that multiple mobile phones shoot is processed, matched by A, generation reduction degree threedimensional model high.B reduces the computational load of smart mobile phone, and introducing cloud processor carries out high load capacity computing；Such as introduce Cloud Server, treatment mass picture and high load capacity three-dimensional computing；Picture and threedimensional model are carried out into compression coding, form conversion, makes data upload, download more quick and smooth.
Description
Technical field：
The invention belongs to computer realm, it is related to a kind of three-dimensional reconstruction system, it is especially a kind of to be based on cell-phone camera and cloud
The reconstructing system and method for the three-dimensional human head of server.
Background technology：
Human body head threedimensional model has a wide range of applications in fields such as medical research, virtual realities.And it is common
Three-dimensional reconstruction operating procedure is more difficult, and the requirement to computer computing capability is higher, and improper general user uses.Therefore, fit
It is particularly important for popular three-dimensional number of people reconstruction technique.
Chinese patent (CN201610296789.9) discloses a kind of augmented reality real-time interaction system and its method, the friendship
Mutual system includes remote collection end and control terminal, and the video information of remote collection end Real-time Collection real world forms available
In being combined to export the source information of augmented reality image with virtual world object, and by the source information teletransmission to described
Control terminal, control terminal receives the source information that is sended over by remote collection end, the source information that it will be received with it is corresponding
Virtual world object details combination and form augmented reality image, and formed enhancing is exported in augmented reality
Real world images.Additionally, remote collection end is provided with driver, control terminal is provided with controller, and controller can be by wirelessly to driving
Device sends motion control signal to control driver to move so that transported at the remote controlled remote collection end of control terminal
It is dynamic, make remote collection end controlled motion and can be by the real world under user's needs the in real time required visual angle state of continuous collection
Video information.Patent collection is video information, and gathered data amount is big, and augmented reality is carried out by video information, pair is set
Standby demanding terminal is higher, is not suitable for common mobile phone.
Chinese patent (CN201610481363.0) discloses a kind of augmented reality system of achievable 3D models live paint
System, including display module, camera module, DBM, pattern recognition module, 3D modeling renderings module, contrast module, 3D
Model color rendering module.When the present invention can realize being dyeed on true picture, the 3D models that augmented reality is presented
Animation also carries out the colouring of corresponding site simultaneously, so as to realize the interaction of people and animation in augmented reality, is no longer limited to animation
Displaying.The patent is only merely to realize the interaction of people and animation in augmented reality, does not realize that the enhancing of said three-dimensional body head shows
It is real.
As described above, common three-dimensional reconstruction operating procedure is more difficult, the requirement to computer computing capability is higher, does not conform to
Suitable general user uses, it is adaptable to which the reconstruction of popular three-dimensional human head is almost blank out.
The content of the invention：
Shortcoming it is an object of the invention to overcome above-mentioned prior art, there is provided one kind is based on cell-phone camera and Cloud Server
Three-dimensional number of people reconstructing system and method, for mobile phone, flat board user provide it is a kind of full-automatic, conveniently three-dimensional people it is nose heave
The service of building, user only by the number of people of desired reconstruction shooting multiple pictures and need to be uploaded to Cloud Server, you can obtain after a few minutes
Threedimensional model is taken, and model can be browsed in cell-phone customer terminal；The present invention is as follows：1 generates feature by image procossing
Point.2 construct every image position relationship in three dimensions by the contrast of characteristic point, matching.3 with each picture feature point
And based on position relationship, tentatively generate threedimensional model.4 recover to have by recovering the illumination condition of threedimensional model, further
The geometrical model of confidence level high.
The purpose of the present invention is achieved through the following technical solutions：
A kind of reconstructing system of the three-dimensional human head based on cell-phone camera and Cloud Server, the reconstructing system is taken by cloud
Business device, client, photo disposal module, three-dimensional reconstruction module, model browsing module are constituted, and Cloud Server carries out high load capacity computing
To reduce the load of smart mobile phone, client possesses upload pictures, browses the function of threedimensional model, and photo disposal module is used for sieving
The picture that choosing, treatment user upload, three-dimensional reconstruction module carrys out parallel computation figure with advanced mass picture three-dimensional reconstruction
The characteristic point of piece, and characteristic point is synthesized threedimensional model, is then filtered, is smoothed, net-shape processed, obtains final three-dimensional
The threedimensional model that server is produced is downloaded to client and shows that in front of the user, user can be with by model, model browsing module
In the display threedimensional model is observed from all angles.
The method of described reconstructing system, in accordance with the following steps：
(1) user shoots multiple pictures from different perspectives to the human body head for wanting to carry out three-dimensional reconstruction, and by installing
Client on smart mobile phone is by photo upload to Cloud Server；
(2) in cloud server end, the SIFT feature of every pictures is calculated；
(3) SIFT feature according to picture is matched, and then is calculated basis matrix and therefrom obtained eigenmatrix, it
Singular value decomposition is carried out to the previous eigenmatrix for obtaining afterwards, matrix decomposition is turned into two parts, a rotating part and one
Displaced portion, then these parameters are optimized by Bundle Adjustment；Calculate displacement, the spin matrix of picture, and shooting
The inner parameter of head；
(4) in cloud server end, according to the characteristic point and camera parameter that obtain, use multi-view stereo (MVS)
Method, generates preliminary threedimensional model；
(5) in cloud server end, using shape-from-shading (SfS) method, by the light for recovering threedimensional model
According to condition, further optimize threedimensional model quality；
(6) threedimensional model that Cloud Server is generated is downloaded to mobile phone terminal by user, by rotation, slide, zoom operations come
Comprehensive observation threedimensional model.
The step (2) is as follows：
A. metric space is built：This is an initialization operation, and Scale-space theory purpose is many of simulated image data
Scale feature；The foundation of image pyramid, for piece image, sets up its image in different scale, makes image in any chi
Degree has corresponding characteristic point；
B. key feature points are found：In order to find the extreme point of metric space, each sampled point will be with its all of phase
Adjoint point compares, see its whether than it image area and scale domain consecutive points it is big or small, test point in the middle of picture and it is same
Totally 26 points compare for 8 consecutive points of yardstick and corresponding 9 × 2 points of neighbouring yardstick, to ensure in metric space and two
Dimension image space all detects extreme point；If a point is in DOG this layer of metric space and bilevel 26 fields
When being maximum or minimum value, it is a characteristic point of the image under the yardstick to be considered as the point；
C. bad characteristic point is removed：This step will remove the very asymmetric pixel of local curvature；
D. give characteristic point assignment one 128 dimension directioin parameter, the characteristic point in every width figure is determined in previous step, be each
Characteristic point calculates a direction, is further calculated according to this direction, using the gradient direction point of key point neighborhood territory pixel
Cloth characteristic is each key point assigned direction parameter, operator is possessed rotational invariance；
E. the generation of key point description:Reference axis is rotated to be the direction of key point first, to ensure rotational invariance,
8 × 8 window is taken centered on key point.
The step (3) is as follows：
In cloud server end, the SIFT feature according to picture is matched, i.e., all of description in image is carried out
Match somebody with somebody, match 128 dimension tables and show two Feature Points Matching successes, and then calculate basis matrix and therefrom obtain eigenmatrix；It
Every pictures position relationship in three dimensions is calculated by structure-from-motion (SFM) afterwards, figure is calculated
The inner parameter of the displacement of piece, spin matrix, and camera；Singular value point namely is carried out to the previous eigenmatrix for obtaining
Solution, two parts, a rotating part and a displaced portion, last re-optimization these parameters are turned into by matrix decomposition.
The step (5) is as follows：
A. according to the pixel value and spatial relationship of image, the brightness value of every bit on threedimensional model is calculated；
B. according to brightness value and preliminary threedimensional model, under illumination condition piecemeal uniformly limitation, three-dimensional space is calculated
Between middle every bit care condition；
C. according to illumination condition and the relation of brightness value, the normal vector of every bit in optimization three dimensions, and then optimize whole
Individual threedimensional model, makes it finer.
Beneficial effects of the present invention：
Multiple photos for not having extraneous information are processed, matched by A, generation reduction degree threedimensional model high.
B reduces the computational load of smart mobile phone, and introducing cloud processor carries out high load capacity computing；Cloud Server is such as introduced, is located
Reason mass picture and the bit arithmetic of high load capacity three；Picture and threedimensional model are carried out into compression coding, form conversion, upload data,
Download more quick and smooth.
Brief description of the drawings
Fig. 1 is system schematic of the invention.
Wherein：1 is client, 2 is Cloud Server, 3 is photo disposal module, 4 is three-dimensional reconstruction module, 5 is that model is clear
Look at module.
Specific embodiment：
The present invention is described in further detail below in conjunction with the accompanying drawings：
As shown in figure 1, the present invention is clear comprising Cloud Server, client, photo disposal module, three-dimensional reconstruction module, model
Look at module.Solve the problems, such as that conventional three-dimensional reconstruction technique complex operation, computing requirement are high, the present invention is processed using Cloud Server
Complicated process of reconstruction.And client leaves behind upload pictures, browses the function of threedimensional model, user's operation can obtain significantly letter
Change.Photo disposal module is used for screening, processing the picture of user's upload.Three-dimensional reconstruction module is three-dimensional with advanced mass picture
Reconstruction technique carrys out the characteristic point of parallel computation picture, and characteristic point is synthesized threedimensional model, is then filtered, smoothed, net
Shape treatment, obtains final threedimensional model.
The threedimensional model that server is produced is downloaded to client and shown in front of the user, Yong Huke by model browsing module
To observe threedimensional model from all angles in the display.Core three-dimensional reconstruction module therein can be subdivided into picture again
Calculated with, parameter, initial model generation, light source recover and the several subordinate's modules of model optimization.Wherein picture match module accounting
The SIFT feature of every pictures is calculated, parameter calculating module is calculated often using structure-from-motion (SFM) method
Pictures position relationship in three dimensions, initial model generation module uses multi-view stereo (MVS) method root
Preliminary threedimensional model is generated according to characteristic point and camera parameter, light source recovers and model optimization module uses shape-from-
Shading (SfS) method further optimizes threedimensional model quality.
1. user shoots multiple pictures from different perspectives to the number of people for wanting to carry out three-dimensional reconstruction, and by installed in intelligence
Client on mobile phone is by photo upload to Cloud Server.Figure below is the example for shooting photo.
2., in cloud server end, the SIFT feature of every pictures is calculated.
Specific steps include：
A. metric space is built：This is an initialization operation, and Scale-space theory purpose is many of simulated image data
Scale feature.The foundation of image pyramid, for piece image, sets up its image in different scale, it is possible in any chi
Degree can have corresponding characteristic point.Three-dimensional reconstruction module photo disposal module Cloud Server model browsing module cell phone customer
End.
B. key point is found：In order to find the extreme point of metric space, each sampled point will be with its all of consecutive points
Compare, see its whether than it image area and scale domain consecutive points it is big or small.Test point and its same yardstick in the middle of picture
8 consecutive points and corresponding 9 × 2 points of neighbouring yardstick totally 26 points compare, to ensure in metric space and X-Y scheme
Image space all detects extreme point.If a point is most in DOG this layer of metric space and bilevel 26 fields
During big or minimum value, it is a characteristic point of the image under the yardstick to be considered as the point.
C. bad characteristic point is removed：This step will remove the very asymmetric pixel of local curvature.
D. give characteristic point assignment one 128 dimension directioin parameter, the characteristic point in every width figure is determined in previous step, be each
Characteristic point calculates a direction, is further calculated according to this direction, using the gradient direction point of key point neighborhood territory pixel
Cloth characteristic is each key point assigned direction parameter, operator is possessed rotational invariance.
E. the generation of key point description:Reference axis is rotated to be the direction of key point first, to ensure rotational invariance.
8 × 8 window is taken centered on key point.
3. in cloud server end, the SIFT feature according to picture is matched, i.e., all of description in image is carried out
Matching, matches 128 dimension tables and shows two Feature Points Matching successes, and then calculate basis matrix and therefrom obtain eigenmatrix.
Every pictures position relationship in three dimensions is calculated by structure-from-motion (SFM) afterwards, is calculated
The inner parameter of the displacement of picture, spin matrix, and camera.Singular value point namely is carried out to the previous eigenmatrix for obtaining
Solution (SVD), two parts, rotation composition and a displacement composition are turned into by matrix decomposition.It is last to pass through Bundle again
Adjustment optimizes these parameters.
4. in cloud server end, using multi-view stereo (MVS) method, according to the characteristic point obtained in step 3
And camera parameter, generate preliminary threedimensional model.
5. in cloud server end, using shape-from-shading (SfS) method, by the illumination for recovering threedimensional model
Condition, further optimizes threedimensional model quality.Concretely comprising the following steps here：
A. according to the pixel value and spatial relationship of image, the brightness value of every bit on threedimensional model is calculated.
B. according to brightness value and preliminary threedimensional model, under illumination condition piecemeal uniformly limitation, three-dimensional space is calculated
Between middle every bit care condition.
C. according to illumination condition and the relation of brightness value, the normal vector of every bit in optimization three dimensions, and then optimize whole
Individual threedimensional model, makes it finer.
6. the threedimensional model that Cloud Server is generated is downloaded to mobile phone terminal by user.User can be by rotation, slip, scaling
Carry out comprehensive observation threedimensional model Deng operation.
The above, is only presently preferred embodiments of the present invention, and any formal limitation is not made to the present invention, though
So the present invention is disclosed above with preferred embodiment, but is not limited to the present invention, any to be familiar with this professional technology people
Member, without departing from the scope of the present invention, when using the method and technology contents of the disclosure above make it is a little more
Move or be modified to the Equivalent embodiments of equivalent variations, as long as being the content without departing from technical solution of the present invention, according to of the invention
Any simple modification, equivalent variations and modification that technical spirit is made to above example, still fall within technical solution of the present invention
In the range of.
Claims (5)
1. a kind of reconstructing system of the three-dimensional human head based on cell-phone camera and Cloud Server, it is characterised in that：The reconstruction
System is made up of Cloud Server, client, photo disposal module, three-dimensional reconstruction module, model browsing module, and Cloud Server is carried out
To reduce the load of smart mobile phone, client possesses upload pictures, browses the function of threedimensional model, photo disposal for high load capacity computing
Module is used for screening, processing the picture of user's upload, and three-dimensional reconstruction module is come with advanced mass picture three-dimensional reconstruction
The characteristic point of parallel computation picture, and characteristic point is synthesized threedimensional model, is then filtered, is smoothed, net-shape processed, is obtained
The threedimensional model that server is produced is downloaded to client and is illustrated in user plane by final threedimensional model, model browsing module
Before, user can observe threedimensional model from all angles in the display.
2. the method for the reconstructing system being based on described in claim 1, it is characterised in that in accordance with the following steps：
(1) user shoots multiple pictures from different perspectives to the human body head for wanting to carry out three-dimensional reconstruction, and by installed in intelligence
Client that can be on mobile phone is by photo upload to Cloud Server；
(2) in cloud server end, the SIFT feature of every pictures is calculated；
(3) SIFT feature according to picture is matched, and then is calculated basis matrix and therefrom obtained eigenmatrix, right afterwards
The eigenmatrix for previously having obtained carries out singular value decomposition, and matrix decomposition is turned into two parts, a rotating part and a displacement
Part, last re-optimization these parameters；Calculate displacement, the spin matrix of picture, and camera inner parameter；
(4) in cloud server end, according to the characteristic point and camera parameter that obtain, multi-view stereo (MVS) sides are used
Method, generates preliminary threedimensional model；
(5) in cloud server end, using shape-from-shading (SfS) method, by the illumination bar for recovering threedimensional model
Part, further optimizes threedimensional model quality；
(6) threedimensional model that Cloud Server is generated is downloaded to mobile phone terminal by user, by rotation, slip, zoom operations come full side
Position observation threedimensional model.
3. the method for the reconstructing system being based on described in claim 2, it is characterised in that the step (2) is as follows：
A. metric space is built：This is an initialization operation, and Scale-space theory purpose is the multiple dimensioned of simulated image data
Feature；The foundation of image pyramid, for piece image, sets up its image in different scale, make image in any yardstick all
There is corresponding characteristic point；
B. key feature points are found：In order to find the extreme point of metric space, each sampled point will be with its all of consecutive points
Compare, see its whether than it image area and scale domain consecutive points it is big or small, test point in the middle of picture and its same yardstick
8 consecutive points and corresponding 9 × 2 points of neighbouring yardstick totally 26 points compare, to ensure in metric space and X-Y scheme
Image space all detects extreme point；If a point is most in DOG this layer of metric space and bilevel 26 fields
During big or minimum value, it is a characteristic point of the image under the yardstick to be considered as the point；
C. bad characteristic point is removed：This step will remove the very asymmetric pixel of local curvature；
D. give characteristic point assignment one 128 dimension directioin parameter, the characteristic point in every width figure is determined in previous step, be each feature
Point calculates a direction, is further calculated according to this direction, and the gradient direction distribution using key point neighborhood territory pixel is special
Property be each key point assigned direction parameter, operator is possessed rotational invariance；
E. the generation of key point description:Reference axis is rotated to be the direction of key point first, to ensure rotational invariance, to close
8 × 8 window is taken centered on key point.
4. the method for the reconstructing system being based on described in claim 2, it is characterised in that the step (3) is as follows：In Cloud Server
End, the SIFT feature according to picture is matched, i.e., all of description in image is matched, and is matched 128 dimension tables and is shown
Two Feature Points Matching successes, and then calculate basis matrix and therefrom obtain eigenmatrix；Pass through structure- afterwards
From-motion (SFM) calculates every pictures position relationship in three dimensions, calculates displacement, the spin moment of picture
Battle array, and camera inner parameter；Singular value decomposition namely is carried out to the previous eigenmatrix for obtaining, matrix decomposition is turned into
Two parts, a rotating part and a displaced portion, last re-optimization these parameters.
5. the method for the reconstructing system being based on described in claim 2, it is characterised in that the step (5) is as follows：
A. according to the pixel value and spatial relationship of image, the brightness value of every bit on threedimensional model is calculated；
B. according to brightness value and preliminary threedimensional model, under illumination condition piecemeal uniformly limitation, in calculating three dimensions
The care condition of every bit；
C. according to illumination condition and the relation of brightness value, the normal vector of every bit in optimization three dimensions, and then optimize whole three
Dimension module, makes it finer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710040536.XA CN106910241A (en) | 2017-01-20 | 2017-01-20 | The reconstructing system and method for the three-dimensional human head based on cell-phone camera and Cloud Server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710040536.XA CN106910241A (en) | 2017-01-20 | 2017-01-20 | The reconstructing system and method for the three-dimensional human head based on cell-phone camera and Cloud Server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106910241A true CN106910241A (en) | 2017-06-30 |
Family
ID=59206612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710040536.XA Pending CN106910241A (en) | 2017-01-20 | 2017-01-20 | The reconstructing system and method for the three-dimensional human head based on cell-phone camera and Cloud Server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106910241A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610169A (en) * | 2017-10-06 | 2018-01-19 | 湖北聚注通用技术研究有限公司 | A kind of decoration construction scene 3-D imaging system |
| CN107734321A (en) * | 2017-09-26 | 2018-02-23 | 韩世民 | A kind of 3D imaging methods based on mobile device |
| CN108446596A (en) * | 2018-02-14 | 2018-08-24 | 天目爱视（北京）科技有限公司 | Iris 3D 4 D datas acquisition system based on Visible Light Camera matrix and method |
| CN108470150A (en) * | 2018-02-14 | 2018-08-31 | 天目爱视（北京）科技有限公司 | A kind of biological characteristic 4 D data acquisition method and device based on Visible Light Camera |
| CN108470186A (en) * | 2018-02-14 | 2018-08-31 | 天目爱视（北京）科技有限公司 | A kind of matching process and device of image characteristic point |
| CN108492330A (en) * | 2018-02-14 | 2018-09-04 | 天目爱视（北京）科技有限公司 | A kind of multi-vision visual depth computing method and device |
| CN108490642A (en) * | 2018-02-14 | 2018-09-04 | 天目爱视（北京）科技有限公司 | Glasses automatic design method based on 3D header datas |
| CN108537236A (en) * | 2018-04-04 | 2018-09-14 | 天目爱视（北京）科技有限公司 | A kind of polyphaser data control system for identifying |
| CN108833796A (en) * | 2018-09-21 | 2018-11-16 | 维沃移动通信有限公司 | A kind of image capturing method and terminal |
| CN109328459A (en) * | 2017-12-29 | 2019-02-12 | 深圳配天智能技术研究院有限公司 | Intelligent terminal and its 3D imaging method, 3D imaging system |
| CN110189408A (en) * | 2019-06-04 | 2019-08-30 | 西安科技大学 | It is a kind of that the system and method for human body appearance data is obtained according to human body photo |
| CN111288970A (en) * | 2020-02-26 | 2020-06-16 | 国网上海市电力公司 | Portable electrified distance measuring device |
| CN111724481A (en) * | 2020-06-24 | 2020-09-29 | 嘉应学院 | Method, device, equipment and storage medium for three-dimensional reconstruction of two-dimensional image |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054291A (en) * | 2009-11-04 | 2011-05-11 | 厦门市美亚柏科信息股份有限公司 | Method and device for reconstructing three-dimensional face based on single face image |
| CN104200517A (en) * | 2014-08-06 | 2014-12-10 | 北京工业大学 | Three-dimensional reconstruction method |
| CN104331924A (en) * | 2014-11-26 | 2015-02-04 | 西安冉科信息技术有限公司 | Three-dimensional reconstruction method based on single camera SFS algorithm |
| JP2015087846A (en) * | 2013-10-29 | 2015-05-07 | 山九株式会社 | Three-dimensional model generation system |
| CN104809755A (en) * | 2015-04-09 | 2015-07-29 | 福州大学 | Single-image-based cultural relic three-dimensional reconstruction method |
| CN106023302A (en) * | 2016-05-06 | 2016-10-12 | 刘进 | Mobile communication terminal, three-dimensional reconstruction method thereof and server |
| CN106097436A (en) * | 2016-06-12 | 2016-11-09 | 广西大学 | A kind of three-dimensional rebuilding method of large scene object |
-
2017
- 2017-01-20 CN CN201710040536.XA patent/CN106910241A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054291A (en) * | 2009-11-04 | 2011-05-11 | 厦门市美亚柏科信息股份有限公司 | Method and device for reconstructing three-dimensional face based on single face image |
| JP2015087846A (en) * | 2013-10-29 | 2015-05-07 | 山九株式会社 | Three-dimensional model generation system |
| CN104200517A (en) * | 2014-08-06 | 2014-12-10 | 北京工业大学 | Three-dimensional reconstruction method |
| CN104331924A (en) * | 2014-11-26 | 2015-02-04 | 西安冉科信息技术有限公司 | Three-dimensional reconstruction method based on single camera SFS algorithm |
| CN104809755A (en) * | 2015-04-09 | 2015-07-29 | 福州大学 | Single-image-based cultural relic three-dimensional reconstruction method |
| CN106023302A (en) * | 2016-05-06 | 2016-10-12 | 刘进 | Mobile communication terminal, three-dimensional reconstruction method thereof and server |
| CN106097436A (en) * | 2016-06-12 | 2016-11-09 | 广西大学 | A kind of three-dimensional rebuilding method of large scene object |
Non-Patent Citations (3)
| Title |
|---|
| XIAOGUANG HAN, KWAN-YEE K. WONG, YIZHOU YU: "《3D Human Model Reconstruction from Sparse Uncalibrated Views》", 《IEEE COMPUTER GRAPHICS AND APPLICATIONS》 * |
| 张琳: "《秦腔变脸APP的设计与实现》", 《中国优秀硕士学位论文全文数据库》 * |
| 徐辛超: "《基于明暗恢复形状的月面地形恢复》", 30 June 2014, 北京：测绘出版社 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107734321A (en) * | 2017-09-26 | 2018-02-23 | 韩世民 | A kind of 3D imaging methods based on mobile device |
| CN107610169A (en) * | 2017-10-06 | 2018-01-19 | 湖北聚注通用技术研究有限公司 | A kind of decoration construction scene 3-D imaging system |
| CN109328459B (en) * | 2017-12-29 | 2021-02-26 | 深圳配天智能技术研究院有限公司 | Intelligent terminal, 3D imaging method thereof and 3D imaging system |
| CN109328459A (en) * | 2017-12-29 | 2019-02-12 | 深圳配天智能技术研究院有限公司 | Intelligent terminal and its 3D imaging method, 3D imaging system |
| WO2019127508A1 (en) * | 2017-12-29 | 2019-07-04 | 深圳配天智能技术研究院有限公司 | Smart terminal and 3d imaging method and 3d imaging system therefor |
| CN108446596A (en) * | 2018-02-14 | 2018-08-24 | 天目爱视（北京）科技有限公司 | Iris 3D 4 D datas acquisition system based on Visible Light Camera matrix and method |
| CN108470150A (en) * | 2018-02-14 | 2018-08-31 | 天目爱视（北京）科技有限公司 | A kind of biological characteristic 4 D data acquisition method and device based on Visible Light Camera |
| CN108470186A (en) * | 2018-02-14 | 2018-08-31 | 天目爱视（北京）科技有限公司 | A kind of matching process and device of image characteristic point |
| CN108492330A (en) * | 2018-02-14 | 2018-09-04 | 天目爱视（北京）科技有限公司 | A kind of multi-vision visual depth computing method and device |
| CN108490642A (en) * | 2018-02-14 | 2018-09-04 | 天目爱视（北京）科技有限公司 | Glasses automatic design method based on 3D header datas |
| CN108537236A (en) * | 2018-04-04 | 2018-09-14 | 天目爱视（北京）科技有限公司 | A kind of polyphaser data control system for identifying |
| CN108833796A (en) * | 2018-09-21 | 2018-11-16 | 维沃移动通信有限公司 | A kind of image capturing method and terminal |
| CN110189408A (en) * | 2019-06-04 | 2019-08-30 | 西安科技大学 | It is a kind of that the system and method for human body appearance data is obtained according to human body photo |
| CN110189408B (en) * | 2019-06-04 | 2023-04-11 | 西安科技大学 | System and method for obtaining human body appearance data according to human body photos |
| CN111288970A (en) * | 2020-02-26 | 2020-06-16 | 国网上海市电力公司 | Portable electrified distance measuring device |
| CN111724481A (en) * | 2020-06-24 | 2020-09-29 | 嘉应学院 | Method, device, equipment and storage medium for three-dimensional reconstruction of two-dimensional image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106910241A (en) | The reconstructing system and method for the three-dimensional human head based on cell-phone camera and Cloud Server | |
| Wang et al. | High-resolution image synthesis and semantic manipulation with conditional gans | |
| CN110569768B (en) | Construction method of face model, face recognition method, device and equipment | |
| CN108305312B (en) | Method and device for generating 3D virtual image | |
| CN110310319B (en) | Illumination-separated single-view human body clothing geometric detail reconstruction method and device | |
| CN110163953A (en) | Three-dimensional facial reconstruction method, device, storage medium and electronic device | |
| CN104008569B (en) | A kind of 3D scene generating method based on deep video | |
| CN102693419B (en) | Super-resolution face recognition method based on multi-manifold discrimination and analysis | |
| Rossi et al. | Graph-based light field super-resolution | |
| WO2024007478A1 (en) | Three-dimensional human body modeling data collection and reconstruction method and system based on single mobile phone | |
| CN116310076A (en) | Three-dimensional reconstruction method, device, equipment and storage medium based on nerve radiation field | |
| CN108053435A (en) | Dynamic realtime three-dimensional rebuilding method and system based on handheld mobile device | |
| CN111861872A (en) | Image face changing method, video face changing method, device, equipment and storage medium | |
| CN114450719A (en) | Human body model reconstruction method, reconstruction system and storage medium | |
| CN106934824B (en) | Global non-rigid registration and reconstruction method for deformable object | |
| TWI750710B (en) | Image processing method and apparatus, image processing device and storage medium | |
| CN112669448B (en) | Virtual data set development method, system and storage medium based on three-dimensional reconstruction technology | |
| CN106683163B (en) | Imaging method and system for video monitoring | |
| CN108537126A (en) | A kind of face image processing system and method | |
| KR102353556B1 (en) | Apparatus for Generating Facial expressions and Poses Reappearance Avatar based in User Face | |
| CN104506872B (en) | A kind of method and device of converting plane video into stereoscopic video | |
| Li et al. | Single image dehazing with an independent detail-recovery network | |
| CN113808277B (en) | Image processing method and related device | |
| CN106855987A (en) | Sense of reality Fashion Show method and apparatus based on model prop | |
| CN107622526A (en) | A kind of method that 3-D scanning modeling is carried out based on mobile phone facial recognition component |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170630 |
|
| RJ01 | Rejection of invention patent application after publication |