CN107358645A - Product method for reconstructing three-dimensional model and its system - Google Patents
Product method for reconstructing three-dimensional model and its system Download PDFInfo
- Publication number
- CN107358645A CN107358645A CN201710425967.8A CN201710425967A CN107358645A CN 107358645 A CN107358645 A CN 107358645A CN 201710425967 A CN201710425967 A CN 201710425967A CN 107358645 A CN107358645 A CN 107358645A
- Authority
- CN
- China
- Prior art keywords
- product
- depth information
- reconstructing
- image
- dimensional model
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims abstract description 36
- 238000013507 mapping Methods 0.000 claims abstract description 24
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 7
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims 1
- 230000033001 locomotion Effects 0.000 description 5
- 238000009499 grossing Methods 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
A kind of product method for reconstructing three-dimensional model and its system, by gathering product image, and after calculating the homography matrix of plane at infinity corresponding to product image, the mapping matrix between product image slices vegetarian refreshments and the coordinate points of actual scene is obtained by Cholesky decomposition methods;Then network flow corresponding to the product is established, the optimal value of computation energy function, obtains the depth information of product surface;Cube is finally established according to depth information and mapping matrix and voxel division is carried out to cube, and then by updating the TSDF of each cube volume elements and being rendered and projected, realize the reconstruction of threedimensional model, the present invention need not demarcate thing, robustness is high, the influence of image deformation is reduced, threedimensional model has high reliability and robustness.
Description
Technical field
The present invention relates to a kind of technology of field of three-dimension modeling, specifically a kind of product based on two dimensional image is three-dimensional
Model reconstruction method and its system.
Background technology
Three-dimensional reconstruction refers to, to object progress three-dimensional modeling, more truly intuitively show product.Three-dimensional based on image
Reconstruction can break through real-time bottleneck so as to obtain good development.Existing three-dimensional reconstruction crosses range request in camera calibration
Equipment precision is high, and limitation is more.Modeling process is complicated during three-dimensional reconstruction, and speed is slow, and reconstruction precision can not meet to require, therefore
It can not be applied on the three-dimensional reconstruction of actual product display model.
The content of the invention
The present invention for prior art most without depth information optimization processing, also not to smooth item, block the place of item
Reason, cause to model the defects of effect is poor, propose a kind of product method for reconstructing three-dimensional model and its system, it is not necessary to thing is demarcated,
Robustness is high, reduces the influence of image deformation, threedimensional model has high reliability and robustness.
The present invention is achieved by the following technical solutions:
The present invention relates to a kind of product method for reconstructing three-dimensional model, by gathering product image, and calculates product image pair
After the homography matrix for the plane at infinity answered, the seat of product image slices vegetarian refreshments and actual scene is obtained by Cholesky decomposition methods
Mapping matrix between punctuate;Then network flow corresponding to the product is established, the optimal value of computation energy function, obtains product
The depth information on surface;Cube is finally established according to depth information and mapping matrix and voxel division is carried out to cube, is entered
And by updating the TSDF (unblind distance function) of each cube volume elements and being rendered and projected, realize threedimensional model
Reconstruction.
Described mapping matrix, is obtained in the following manner:
1) the homography matrix H of plane at infinity is established∞, and haveSolve homography matrix H∞;
2) according to H∞=KRtK-1, the seat of product image slices vegetarian refreshments and actual scene is solved using Cholesky decomposition methods
Mapping matrix K between punctuate.
The depth information of described product surface, is obtained in the following manner:
A) virtual network of product is established, and energy function is established with the pixel point coordinates of product image;
B) by the way that similarity cost and smooth cost are the grid assignment in virtual network to form network flow;
C) energy function is optimized using the solution annual reporting law of max-flow/minimal cut problem, obtains the depth letter of product surface
Breath.
Described energy function is:
E (f)=∑p∈P[Il(Tranl(xp,yp,fp))-Ir(Tranr(xp,yp,fp))]2+∑(p,q)∈Nu{p,q}|fp-fq|,
Wherein:IlAnd IrFor the picture element matrix of product image, (xp,yp) turn for mesh point coordinate value in the plane of base, Tran for coordinate system
Exchange the letters number, f are pixel to the mapping relations between label, and P is the set of all pixels of the image of definition, and p, q are pixel
Single pixel in set P.
Described reconstruction, specifically includes following steps:
I) bilateral filtering is carried out to depth information;
Ii depth map) is obtained according to depth information, carrying out back projection to depth map obtains vertex graph and each summit
Normal vector;
Iii product image pixel) is transformed into by world coordinate system according to mapping matrix K;
Iv) establish cube and carry out voxel division, and update the TSDF of each volume elements;
V) rendered and projected according to TSDF, generate product threedimensional model.
Described unblind distance function is tape symbol of the volume elements to the nearest surface, the i.e. surface of model of institute's established model
Distance, i.e. symbol represent the context relative to surface;Regard cube due to space will be rebuild, voxel is volume element
Referred to as, it is least unit of the numerical data in three dimensions segmentation, similar to the pixel of two dimensional image.Volume elements represents to determine
A series of voxels (only z coordinate change) of (x, y) coordinate, the TSDF negative number representations finally obtained are being rebuild outside object, 0 table
Show and rebuilding body surface, it is positive number to rebuild interior of articles.
The present invention relates to a kind of product reconstructing three-dimensional model system, including:Camera calibration module, Depth Information Acquistion module
And model building module, wherein:Camera calibration module gathers product image, obtains the coordinate points of image slices vegetarian refreshments and actual scene
Between mapping matrix;Depth Information Acquistion module obtains the depth information of product;Model building module receive mapping matrix and
Depth information, rendered projection obtain the threedimensional model of product.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the present invention.
Embodiment
The present embodiment is related to a kind of product reconstructing three-dimensional model system for realizing the above method, including:Camera calibration module,
Depth Information Acquistion module and model building module, wherein:Camera calibration module gather product image, obtain image slices vegetarian refreshments with
Mapping matrix between the coordinate points of actual scene;Depth Information Acquistion module obtains the depth information of product;Model establishes mould
Block receives mapping matrix and depth information, rendered projection obtain the threedimensional model of product.
As shown in figure 1, for the product method for reconstructing three-dimensional model of said system, comprise the following steps:
Implement to set:For opening up car, control camera does a translational motion and 2 arbitrary motions, shoots 4 photos and (shines
Piece pixel is 1200w);
Software and hardware requirement:Intel (R) Core (TM) i5-3210M CPU@2.5GHz, video card GTX970.
1) the homography matrix H of plane at infinity corresponding to product image is solved∞, and produced using Cholesky decomposition methods
Mapping matrix K between product image slices vegetarian refreshments and the coordinate points of actual scene.The camera of collection product image takes translational motion
Photo is shot with the mode of multiple arbitrary motion, obtains product image.
1.1) the homography matrix H of plane at infinity is established∞。
1.2) according to equation groupSolve homography matrix H∞, wherein:e1、e2For product image after motion
Limit, H1、H2For the homography matrix of space plane, a1And a2For scalar, X1And X2For column vector.
1.3) according to the different homography matrix H tried to achieve∞, according to formula H∞=KRtK-1, and asked using Cholesky decomposition methods
Solve mapping matrix K.
2) network flow corresponding to product is established, the optimal value of computation energy function, obtains the depth information of product surface.
2.1) virtual network of product is established.According to coordinate position of the product in world coordinate system, tridimensional virtual is established
Network, need to rebuild that product is fully wrapped around wherein, be put down using that section of foremost as the substrate of whole cubic network
Face, to the position where the nexus on each base plane, determine which section the object point on product surface falls on, each
Depth Information Acquistion problem, is so just converted into each in virtual three-dimensional cellular Base plane by the corresponding label of section
Individual nexus carries out the problem of depth label.
2.2) energy function is established with product image pixel point coordinates.Energy function is used for representing the property information of image,
Mainly by data constraint item, Smoothing Constraint item and block a three parts and form.The constraints of data constraint is:Work as base plane
On mesh point not by correct label when, the potential object point in world coordinate system at incorrect depth label is projected
Image pixel coordinates system in picture point expressed by Pixel Information be inconsistent;Only meet it in the depth label assigned
In the case of real depth, what picture point just reflected is the Pixel Information of same object point, and the cost of this depth label is only minimum.
Smoothness constraint represents the restriction relation between adjacent pixel pair, can cause Smoothing Constraint when the gap between adjacent pixel is larger
Item increase, so as to cause energy function to increase, Smoothing Constraint item reacts the smooth degree of burst by this method.Block item about
Beam condition is:When the data item cost of all depth labels is both greater than a certain threshold value, that is, set the point of this body surface
It is blocked, by increasing the parameter value of its smoothness constraint, smooth place is done with the depth for causing this point to be referred to object point around it
Reason.
2.3) it is the grid assignment of virtual network to form network flow by similarity cost and smooth cost.Similarity generation
Valency is obtained by SAD local matchings.
2.4) energy function is optimized using the solution annual reporting law of max-flow/minimal cut problem, obtains the depth of product surface
Information.
The solution annual reporting law of described max-flow/minimal cut problem includes but is not limited to Push-Relabel methods and Ford-
Fulkerson methods.
3) according to depth information and mapping matrix K establish cube and to cube carry out voxel division, then render with
Projection obtains product threedimensional model.
3.1) bilateral filtering is carried out to depth information, has carried out noise reduction.
3.2) depth map is obtained according to depth information, carrying out back projection to depth map obtains vertex graph and each summit
Normal vector.
3.3) product image pixel is transformed into by world coordinate system according to mapping matrix K.
3.4) establish cube and carry out voxel division, and update the TSDF of each volume elements., will to each frame product image
Each volume elements is transformed into camera coordinates system and projects to product image coordinate point, if in drop shadow spread, updates TSDF.
3.5) rendered and projected according to TSDF, generate product threedimensional model.
Compared with prior art, the present invention need not demarcate thing, and robustness is high, reduces the influence of image deformation, three-dimensional
Model has high reliability and robustness, and computing resource only needs common commercialized GPU, and modeling speed improves 7.3%.
Above-mentioned specific implementation can by those skilled in the art on the premise of without departing substantially from the principle of the invention and objective with difference
Mode local directed complete set is carried out to it, protection scope of the present invention is defined by claims and not by above-mentioned specific implementation institute
Limit, each implementation in the range of it is by the constraint of the present invention.
Claims (7)
1. a kind of product method for reconstructing three-dimensional model, it is characterised in that by gathering product image, and it is corresponding to calculate product image
Plane at infinity homography matrix after, pass through the coordinate that Cholesky decomposition methods obtain product image slices vegetarian refreshments and actual scene
Mapping matrix between point;Then network flow corresponding to the product is established, the optimal value of computation energy function, obtains product table
The depth information in face;Cube is finally established according to depth information and mapping matrix and voxel division is carried out to cube, and then
By updating the TSDF of each cube volume elements and being rendered and projected, the reconstruction of threedimensional model is realized.
2. product method for reconstructing three-dimensional model according to claim 1, it is characterized in that, described mapping matrix, by with
Under type obtains:
1.1) the homography matrix H of plane at infinity is established∞, and haveSolve homography matrix H∞;
1.2) according to H∞=KRtK-1, the coordinate of product image slices vegetarian refreshments and actual scene is solved using Cholesky decomposition methods
Mapping matrix K between point.
3. product method for reconstructing three-dimensional model according to claim 1, it is characterized in that, the depth letter of described product surface
Breath, is obtained in the following manner:
2.1) virtual network of product is established, and energy function is established with the pixel point coordinates of product image;
2.2) by the way that similarity cost and smooth cost are the grid assignment in virtual network to form network flow;
2.3) energy function is optimized using the solution annual reporting law of max-flow/minimal cut problem, obtains the depth information of product surface.
4. product method for reconstructing three-dimensional model according to claim 3, it is characterized in that, described energy function be E (f)=
∑p∈P[Il(Tranl(xp, yp,fp))-Ir(Tranr(xp, yp,fp))]2+∑(p,q)∈Nu{ p, q }|fp-fq|, wherein:IlAnd IrFor production
The picture element matrix of product image, (xp,yp) it is mesh point coordinate value in the plane of base, Tran is coordinate system transfer function, and f is pixel
Point is the set of all pixels of the image of definition to the mapping relations between label, P, and p, q are picture single in pixel set P
Vegetarian refreshments.
5. product method for reconstructing three-dimensional model according to claim 4, it is characterized in that, described max-flow/minimal cut is asked
The solution annual reporting law of topic includes:Push-Relabel methods and Ford-Fulkerson methods.
6. product method for reconstructing three-dimensional model according to claim 3, it is characterized in that, described reconstruction, specifically include with
Lower step:
3.1) bilateral filtering is carried out to depth information;
3.2) depth map is obtained according to depth information, carrying out back projection to depth map obtains the normal direction on vertex graph and each summit
Amount;
3.3) product image pixel is transformed into by world coordinate system according to mapping matrix K;
3.4) establish cube and carry out voxel division, and update the TSDF of each volume elements;
3.5) rendered and projected according to TSDF, generate product threedimensional model.
A kind of 7. product reconstructing three-dimensional model system for realizing the above method, it is characterised in that including:Camera calibration module, depth
Data obtaining module and model building module are spent, wherein:Camera calibration module gathers product image, obtains image slices vegetarian refreshments and reality
Mapping matrix between the coordinate points of border scene;Depth Information Acquistion module obtains the depth information of product;Model building module
Receive mapping matrix and depth information, rendered projection obtain the threedimensional model of product.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710425967.8A CN107358645B (en) | 2017-06-08 | 2017-06-08 | Product three-dimensional model reconstruction method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710425967.8A CN107358645B (en) | 2017-06-08 | 2017-06-08 | Product three-dimensional model reconstruction method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107358645A true CN107358645A (en) | 2017-11-17 |
CN107358645B CN107358645B (en) | 2020-08-11 |
Family
ID=60273557
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710425967.8A Active CN107358645B (en) | 2017-06-08 | 2017-06-08 | Product three-dimensional model reconstruction method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107358645B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062788A (en) * | 2017-12-18 | 2018-05-22 | 北京锐安科技有限公司 | A kind of three-dimensional rebuilding method, device, equipment and medium |
WO2019219012A1 (en) * | 2018-05-15 | 2019-11-21 | 清华大学 | Three-dimensional reconstruction method and device uniting rigid motion and non-rigid deformation |
CN110489834A (en) * | 2019-08-02 | 2019-11-22 | 广州彩构网络有限公司 | A kind of designing system for actual products threedimensional model |
CN111696145A (en) * | 2019-03-11 | 2020-09-22 | 北京地平线机器人技术研发有限公司 | Depth information determination method, depth information determination device and electronic equipment |
CN111788610A (en) * | 2017-12-22 | 2020-10-16 | 奇跃公司 | Viewpoint-dependent brick selection for fast volumetric reconstruction |
CN114241029A (en) * | 2021-12-20 | 2022-03-25 | 贝壳技术有限公司 | Image three-dimensional reconstruction method and device |
WO2022227875A1 (en) * | 2021-04-29 | 2022-11-03 | 中兴通讯股份有限公司 | Three-dimensional imaging method, apparatus, and device, and storage medium |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1395222A (en) * | 2001-06-29 | 2003-02-05 | 三星电子株式会社 | Representation and diawing method of three-D target and method for imaging movable three-D target |
US7212201B1 (en) * | 1999-09-23 | 2007-05-01 | New York University | Method and apparatus for segmenting an image in order to locate a part thereof |
CN101262619A (en) * | 2008-03-30 | 2008-09-10 | 深圳华为通信技术有限公司 | Method and device for capturing view difference |
CN101751697A (en) * | 2010-01-21 | 2010-06-23 | 西北工业大学 | Three-dimensional scene reconstruction method based on statistical model |
CN101833786A (en) * | 2010-04-06 | 2010-09-15 | 清华大学 | Method and system for capturing and rebuilding three-dimensional model |
CN101998136A (en) * | 2009-08-18 | 2011-03-30 | 华为技术有限公司 | Homography matrix acquisition method as well as image pickup equipment calibrating method and device |
CN102682467A (en) * | 2011-03-15 | 2012-09-19 | 云南大学 | Plane- and straight-based three-dimensional reconstruction method |
CN102800081A (en) * | 2012-06-06 | 2012-11-28 | 天津大学 | Expansion algorithm of high-noise resistance speckle-coated phase diagram based on image cutting |
CN103198523A (en) * | 2013-04-26 | 2013-07-10 | 清华大学 | Three-dimensional non-rigid body reconstruction method and system based on multiple depth maps |
CN104599314A (en) * | 2014-06-12 | 2015-05-06 | 深圳奥比中光科技有限公司 | Three-dimensional model reconstruction method and system |
CN104899883A (en) * | 2015-05-29 | 2015-09-09 | 北京航空航天大学 | Indoor object cube detection method for depth image scene |
CN105046743A (en) * | 2015-07-01 | 2015-11-11 | 浙江大学 | Super-high-resolution three dimensional reconstruction method based on global variation technology |
CN106355621A (en) * | 2016-09-23 | 2017-01-25 | 邹建成 | Method for acquiring depth information on basis of array images |
CN106373153A (en) * | 2016-09-23 | 2017-02-01 | 邹建成 | Array lens-based 3D image replacement technology |
CN106651926A (en) * | 2016-12-28 | 2017-05-10 | 华东师范大学 | Regional registration-based depth point cloud three-dimensional reconstruction method |
CN106709948A (en) * | 2016-12-21 | 2017-05-24 | 浙江大学 | Quick binocular stereo matching method based on superpixel segmentation |
CN106803267A (en) * | 2017-01-10 | 2017-06-06 | 西安电子科技大学 | Indoor scene three-dimensional rebuilding method based on Kinect |
-
2017
- 2017-06-08 CN CN201710425967.8A patent/CN107358645B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7212201B1 (en) * | 1999-09-23 | 2007-05-01 | New York University | Method and apparatus for segmenting an image in order to locate a part thereof |
CN1395222A (en) * | 2001-06-29 | 2003-02-05 | 三星电子株式会社 | Representation and diawing method of three-D target and method for imaging movable three-D target |
CN101262619A (en) * | 2008-03-30 | 2008-09-10 | 深圳华为通信技术有限公司 | Method and device for capturing view difference |
CN101998136A (en) * | 2009-08-18 | 2011-03-30 | 华为技术有限公司 | Homography matrix acquisition method as well as image pickup equipment calibrating method and device |
CN101751697A (en) * | 2010-01-21 | 2010-06-23 | 西北工业大学 | Three-dimensional scene reconstruction method based on statistical model |
CN101833786A (en) * | 2010-04-06 | 2010-09-15 | 清华大学 | Method and system for capturing and rebuilding three-dimensional model |
CN102682467A (en) * | 2011-03-15 | 2012-09-19 | 云南大学 | Plane- and straight-based three-dimensional reconstruction method |
CN102800081A (en) * | 2012-06-06 | 2012-11-28 | 天津大学 | Expansion algorithm of high-noise resistance speckle-coated phase diagram based on image cutting |
CN103198523A (en) * | 2013-04-26 | 2013-07-10 | 清华大学 | Three-dimensional non-rigid body reconstruction method and system based on multiple depth maps |
CN104599314A (en) * | 2014-06-12 | 2015-05-06 | 深圳奥比中光科技有限公司 | Three-dimensional model reconstruction method and system |
CN104899883A (en) * | 2015-05-29 | 2015-09-09 | 北京航空航天大学 | Indoor object cube detection method for depth image scene |
CN105046743A (en) * | 2015-07-01 | 2015-11-11 | 浙江大学 | Super-high-resolution three dimensional reconstruction method based on global variation technology |
CN106355621A (en) * | 2016-09-23 | 2017-01-25 | 邹建成 | Method for acquiring depth information on basis of array images |
CN106373153A (en) * | 2016-09-23 | 2017-02-01 | 邹建成 | Array lens-based 3D image replacement technology |
CN106709948A (en) * | 2016-12-21 | 2017-05-24 | 浙江大学 | Quick binocular stereo matching method based on superpixel segmentation |
CN106651926A (en) * | 2016-12-28 | 2017-05-10 | 华东师范大学 | Regional registration-based depth point cloud three-dimensional reconstruction method |
CN106803267A (en) * | 2017-01-10 | 2017-06-06 | 西安电子科技大学 | Indoor scene three-dimensional rebuilding method based on Kinect |
Non-Patent Citations (3)
Title |
---|
NHAT QUANG DO ET AL: "Leap Studio -- A Virtual Interactive 3D Modeling Application Based on WebGL", 《2014 5TH INTERNATIONAL CONFERENCE ON DIGITAL HOME》 * |
WEI-MING CHEN ET AL: "Improving Graph Cuts algorithm to transform sequence of stereo image to depth map", 《JOURNAL OF SYSTEMS AND SOFTWARE》 * |
冯树彪: "基于图像的三维重建", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062788A (en) * | 2017-12-18 | 2018-05-22 | 北京锐安科技有限公司 | A kind of three-dimensional rebuilding method, device, equipment and medium |
US11321924B2 (en) | 2017-12-22 | 2022-05-03 | Magic Leap, Inc. | Caching and updating of dense 3D reconstruction data |
CN114332332A (en) * | 2017-12-22 | 2022-04-12 | 奇跃公司 | Method and apparatus for generating a three-dimensional reconstruction of a surface in a scene |
CN114332332B (en) * | 2017-12-22 | 2023-08-18 | 奇跃公司 | Method and device for generating a three-dimensional reconstruction of a surface in a scene |
CN111788610A (en) * | 2017-12-22 | 2020-10-16 | 奇跃公司 | Viewpoint-dependent brick selection for fast volumetric reconstruction |
CN111788610B (en) * | 2017-12-22 | 2021-11-26 | 奇跃公司 | Method and apparatus for generating a three-dimensional reconstruction of a surface in a scene |
US11263820B2 (en) | 2017-12-22 | 2022-03-01 | Magic Leap, Inc. | Multi-stage block mesh simplification |
US11580705B2 (en) | 2017-12-22 | 2023-02-14 | Magic Leap, Inc. | Viewpoint dependent brick selection for fast volumetric reconstruction |
US11398081B2 (en) | 2017-12-22 | 2022-07-26 | Magic Leap, Inc. | Method of occlusion rendering using raycast and live depth |
WO2019219012A1 (en) * | 2018-05-15 | 2019-11-21 | 清华大学 | Three-dimensional reconstruction method and device uniting rigid motion and non-rigid deformation |
CN111696145A (en) * | 2019-03-11 | 2020-09-22 | 北京地平线机器人技术研发有限公司 | Depth information determination method, depth information determination device and electronic equipment |
CN111696145B (en) * | 2019-03-11 | 2023-11-03 | 北京地平线机器人技术研发有限公司 | Depth information determining method, depth information determining device and electronic equipment |
CN110489834A (en) * | 2019-08-02 | 2019-11-22 | 广州彩构网络有限公司 | A kind of designing system for actual products threedimensional model |
WO2022227875A1 (en) * | 2021-04-29 | 2022-11-03 | 中兴通讯股份有限公司 | Three-dimensional imaging method, apparatus, and device, and storage medium |
CN114241029A (en) * | 2021-12-20 | 2022-03-25 | 贝壳技术有限公司 | Image three-dimensional reconstruction method and device |
Also Published As
Publication number | Publication date |
---|---|
CN107358645B (en) | 2020-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107358645A (en) | Product method for reconstructing three-dimensional model and its system | |
CN101404091B (en) | Three-dimensional human face reconstruction method and system based on two-step shape modeling | |
CN109003325B (en) | Three-dimensional reconstruction method, medium, device and computing equipment | |
CN106067190B (en) | A kind of generation of fast face threedimensional model and transform method based on single image | |
CN106910242A (en) | The method and system of indoor full scene three-dimensional reconstruction are carried out based on depth camera | |
CN101916454B (en) | Method for reconstructing high-resolution human face based on grid deformation and continuous optimization | |
CN111768477B (en) | Three-dimensional facial expression base establishment method and device, storage medium and electronic equipment | |
CN104616286B (en) | Quick semi-automatic multi views depth restorative procedure | |
CN114863059A (en) | Method and system for detecting and combining structural features in 3D reconstruction | |
CN112734890B (en) | Face replacement method and device based on three-dimensional reconstruction | |
US11928778B2 (en) | Method for human body model reconstruction and reconstruction system | |
CN109147025B (en) | RGBD three-dimensional reconstruction-oriented texture generation method | |
CN112651881B (en) | Image synthesizing method, apparatus, device, storage medium, and program product | |
US20230086928A1 (en) | Light field reconstruction method and apparatus of a dynamic scene | |
CN112308918A (en) | Unsupervised monocular vision odometer method based on pose decoupling estimation | |
CN115668300A (en) | Object reconstruction with texture resolution | |
CN111951368A (en) | Point cloud, voxel and multi-view fusion deep learning method | |
CN111402403B (en) | High-precision three-dimensional face reconstruction method | |
CN111209811A (en) | Method and system for detecting eyeball attention position in real time | |
CN100487732C (en) | Method for generating cartoon portrait based on photo of human face | |
CN110070605A (en) | A kind of unmarked movement catching method of real-time body | |
CN114913552B (en) | Three-dimensional human body density corresponding estimation method based on single-view-point cloud sequence | |
CN103049929A (en) | Multi-camera dynamic scene 3D (three-dimensional) rebuilding method based on joint optimization | |
CN115496862A (en) | Real-time three-dimensional reconstruction method and system based on SPIN model | |
CN116152442B (en) | Three-dimensional point cloud model generation method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240401 Address after: 201203 Pudong New Area, Shanghai, China (Shanghai) free trade trial area, No. 3, 1 1, Fang Chun road. Patentee after: SHANGHAI HANYU BIOLOGICAL SCIENCE & TECHNOLOGY Co.,Ltd. Country or region after: China Address before: 200240 No. 800, Dongchuan Road, Shanghai, Minhang District Patentee before: SHANGHAI JIAO TONG University Country or region before: China |