CN108269271A - A kind of clothes expose the false with human body image, match the method and system migrated - Google Patents
A kind of clothes expose the false with human body image, match the method and system migrated Download PDFInfo
- Publication number
- CN108269271A CN108269271A CN201810034021.3A CN201810034021A CN108269271A CN 108269271 A CN108269271 A CN 108269271A CN 201810034021 A CN201810034021 A CN 201810034021A CN 108269271 A CN108269271 A CN 108269271A
- Authority
- CN
- China
- Prior art keywords
- clothes
- image
- human body
- false
- body 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A kind of method that clothes expose the false with human body image, match migration, including reading the three-dimensional data of model and the shooting image of clothes；Camera projection matrix is calculated, and obtains model's projected image；Garment data is added to projected image, and carries out repair process of exposing the false, the garment data repaired；The garment data of reparation is moved on target body image, is finally exposed the false and matched the human body image of migration.The present invention handles the image of clothing under different shooting environmentals, is allowed on the human body image being through under different visual angles.It is influenced by shooting angle, shooting distance, the first-class parameter of imaging lens, and size, the style difference of different garment increase the difficulty that its texture, profile are kept in clothes transition process, therefore it employs and first clothes with the human body image projected is matched and carry out reparation of exposing the false, then the garment data after reparation is moved to the matching shift function that the mode on the human body image of final rendering realizes clothes and human body image again.
Description
Technical field
The present invention relates to computer graphics and technical field of computer vision more particularly to a kind of clothes and human body image
It exposes the false, match the method and system migrated.
Background technology
The matching migration of clothes and human body image, is exactly before unobvious change the information such as clothes illumination, profile, texture
It puts and the garment data under different shooting environmentals is through on same human body image.Since three-dimensional garment data scanning, segmentation need
A large amount of manpower is wanted to handle by hand, this is apparent undesirable under conditions of high-volume clothes material to needing to handle, in addition, two dimension clothes
Data are filled due to the otherness of shooting angle, it is impossible to directly it is directly matched with the human body image under same posture, therefore this
Invention employs a kind of clothes and is asked from the matching migrating technology of human body image to solve the migration of the clothes under different shooting environmentals
Topic.
Invention content
The present invention provides a kind of method that clothes expose the false with human body image, match migration, including,
Read the three-dimensional data of model and the shooting image of clothes；
Camera projection matrix is calculated, and obtains model's projected image；
Garment data is added to projected image, and carries out repair process of exposing the false, the garment data repaired；
The garment data of reparation is moved on target body image, is finally exposed the false and matched the human figure of migration
Picture.
Further, the three-dimensional data of the reading model and the two dimensional image of clothes shooting, including,
Model is to carry the nude model of scaling board in two hands and the crown respectively, and three dimensional point cloud is to pass through high-precision
Vis scan rebuild to obtain；
The two dimensional image of clothes shooting is needed comprising EXIF information (exchangeable image file), while in order to avoid clothes move
Occur the excessive situation of visual angle, light differential after moving on on new human body image, thus need to limit clothes shooting flow
System.
Further, the calculating camera projection matrix, and the projected image of entity model is obtained, including,
Calculate camera projection matrix：
The purpose for calculating camera projection matrix is to obtain the human body contour outline in shooting figure under clothes, can be analyzed to two
The product of a matrix：
P=K [R | T]
Wherein, P is camera projection matrix, and K is camera internal reference matrix, and expression-form is
Fx, fy, px, py are respectively X, focal length and principal point offset in Y-direction, can be directly from the EXIF information of image
Middle reading, [R | T] it is Camera extrinsic matrix, expression-form is
θ is around X, Y, Z coordinate axis rotation angle, Tx, Ty respectively, and Tz is X respectively, Y, the translational movement of Z coordinate axis；
Match the acquisition of point set and the generation of projected image：
Characteristic point need to be chosen manually on scaling board in three-dimensional point cloud, and the characteristic point of scaling board can pass through angle in shooting figure
Point detecting method extracts, and projected image uses OPENGL (Open Graphics Library after projection matrix is calculated
Open graphic library) rendered.
Further, it is described garment data to be added to projected image, and carry out repair process of exposing the false, it is repaired
Garment data, including,
Mesh generation is searched with match point；
The regular quadrilateral grid of 20*30 is divided into for the image that size is 800*1200, extracts clothes respectively first
Profile and human body contour outline point set, and calculate the direction vector of each profile point；Then, human body contour outline point set is traversed, passes through direction
Angle between vector and the distance between 2 points are as criterion, and by the way of one-to-many matching, from clothes profile
Matching coordinate points are searched in point；
Target gridding calculates：
Characteristic point energy equation
Local Phase is to rigid energy equation
The energy equation of straight-line segment.
Further, the target gridding calculates, including,
Straight-line segment constraint and Local Phase are added to during target gridding is calculated to rigid constraint, and is employed
The mode for following harm reason is iterated optimization, so as to which target gridding be made more to stablize.Present invention incorporates characteristic point, Local Phases pair
The constraintss such as rigidity and straight-line segment carry out calculating target gridding position, are exactly to minimize energy equation for simplification：
Min | | E | |=min | | α Ef+βEs+γEl||
Wherein, Ef, Es, ElRespectively the energy equation of characteristic point, relative stiffness and straight-line segment, α, beta, gamma are respectively
Its weight parameter.
Further, the characteristic point energy equation：
Wherein, PkIt is characterized target coordinate position a little, VkA little corresponding four mesh vertex coordinates are characterized,It is four
The weight parameter of a grid.In actual treatment, give each characteristic point different weights according to the distance between match point.
Further, the Local Phase is to rigid energy equation：
Es(V1)=| | V1-(V2+u(V3-V2)+v(R90(V3-V2)))||2
For a vertex V1 of arbitrary triangle, exist between other two vertex V2, V3 of triangle with
Co-relation, therefore the energy equation is added as constraints during target gridding vertex position is calculated, it can keep taking
The local relative stiffness of dress.
Further, the energy equation of the straight-line segment：
The detection of straight-line segment has used a kind of line segmentation algorithm (a line segment detector, LSD), should
Algorithm does not need to adjusting parameter, and the testing result of subpixel accuracy, derivation of energy formula can be obtained within the linear time
For：
Wherein, Lb, LcFor two extreme coordinates of line segment, N is the decile hop count of the line segment,For line bisection coordinate bit
Put, in practical solution procedure by Along ent each on line segment by it where four vertex of grid be indicated.
Further, the garment data of reparation is moved on target body image, is finally exposed the false and matched migration
Human body image, including,
The matching relationship between projection human body contour outline and target body profile is used to be taken to drive quadrilateral mesh to realize
Fill shift function：
Division rule quadrilateral mesh；
According to the human joint points of projection and the matching relationship of target body artis, the pairing calculated between profile point is closed
System；
Target gridding apex coordinate is calculated according to the solution procedure that target gridding calculates；
The shift function of garment data is realized by the driving of grid.
The present invention provides the system that a kind of clothes expose the false with human body image, match migration, including,
Read module reads the three-dimensional data of model and the shooting image of clothes；
Acquisition module calculates camera projection matrix, and obtains model's projected image；
Garment data is added to projected image, and carries out repair process of exposing the false by processing module, the clothes number repaired
According to；
Generation module, the garment data of reparation is moved on target body image, is finally exposed the false and matched migration
Human body image.
The present invention provides the product that a kind of clothes expose the false with human body image, match migration, which is characterized in that including being suitable for
The image of virtual reality, virtual fitting, virtual social, clothes, footwear and accessories and non-genuine exposure body.
Advantageous effect
The present invention proposes the method and system that a kind of clothes expose the false with human body image, match migration, by different shooting rings
Image of clothing under border is handled, and is allowed on the human body image being through under different visual angles.By shooting angle, shooting distance, into
As the influence of the parameters such as camera lens and size, the style difference of different garment increase and its line kept in clothes transition process
Reason, the difficulty of profile, therefore employ and first clothes with the human body image projected are matched and carry out reparation of exposing the false, then it will repair again
The mode that garment data after multiple is moved on the human body image of final rendering realizes the matching migration work(of clothes and human body image
Energy.
Description of the drawings
Fig. 1 is that schematic diagram is built by studio
Fig. 2 is clothes shooting schematic diagram
Fig. 3 is three-dimensional data drop shadow effect figure
Fig. 4 is that clothes are exposed the false exemplary plot
Fig. 5 is that clothes are exposed the false repairing effect figure
Fig. 6 is clothes migration effect figure
Specific embodiment
A kind of method exposed the false the present embodiment provides clothes with human body image, match migration, including,
Read the three-dimensional data of model and the shooting image of clothes；
Camera projection matrix is calculated, and obtains model's projected image；
Garment data is added to projected image, and carries out repair process of exposing the false, the garment data repaired；
The garment data of reparation is moved on target body image, is finally exposed the false and matched the human figure of migration
Picture.
Preferred embodiment reads the three-dimensional data of model and the two dimensional image of clothes shooting in the present embodiment, including,
Model is to carry the nude model of scaling board in two hands and the crown respectively, and three dimensional point cloud is to pass through high-precision
Vis scan rebuild to obtain；
The two dimensional image of clothes shooting is needed comprising EXIF information (exchangeable image file), while in order to avoid clothes move
Occur the excessive situation of visual angle, light differential after moving on on new human body image, thus need to limit clothes shooting flow
System.
Clothes are shot：
Shooting studio builds
Background cloth of the pure color cloth not less than 3m*3m as studio is chosen, height is built and is at least 2.5m.And suggest studio
(4m*5m) is built in independent room, avoids influence of the various light sources to shooting environmental as possible.(signal is built by Fig. 1, studio
Figure)
Pedestal is first well placed by model, then places model；The clothes for needing to shoot are put on, install scaling board.
Ensure the stability of shooting, camera trivets please be use, be placed into front of background cloth.Camera it is vertical with ground away from
From being 120 centimetres, the distance of camera corresponding points vertical with ground and model's bottom plate is 255 centimetres.(Fig. 3, clothes shooting signal
Figure)
Camera is debugged and calibration
Lens focus is 50mm；
Camera heights are 120cm；
Image quality is set as standard, exports RAW image, picture format JPEG.
Preferred embodiment calculates camera projection matrix in the present embodiment, and obtains the projected image of entity model, including,
Calculate camera projection matrix：
The purpose for calculating camera projection matrix is to obtain the human body contour outline in shooting figure under clothes, can be analyzed to two
The product of a matrix：
P=K [R | T]
Wherein, P is camera projection matrix, and K is camera internal reference matrix, and expression-form is
Fx, fy, px, py are respectively X, focal length and principal point offset in Y-direction, can be directly from the EXIF information of image
Middle reading, [R | T] it is Camera extrinsic matrix, expression-form is
θ is around X, Y, Z coordinate axis rotation angle, Tx, Ty respectively, and Tz is X respectively, Y, the translational movement of Z coordinate axis；
Match the acquisition of point set and the generation of projected image：
Characteristic point need to be chosen manually on scaling board in three-dimensional point cloud, and the characteristic point of scaling board can pass through angle in shooting figure
Point detecting method extracts, and projected image uses OPENGL (Open Graphics Library after projection matrix is calculated
Open graphic library) rendered.
Garment data is added to projected image in the present embodiment, and carries out repair process of exposing the false by preferred embodiment, obtains
The garment data of reparation, including,
Mesh generation is searched with match point；
The regular quadrilateral grid of 20*30 is divided into for the image that size is 800*1200, extracts clothes respectively first
Profile and human body contour outline point set, and calculate the direction vector of each profile point；Then, human body contour outline point set is traversed, passes through direction
Angle between vector and the distance between 2 points are as criterion, and by the way of one-to-many matching, from clothes profile
Matching coordinate points are searched in point；
Target gridding calculates：
Characteristic point energy equation
Local Phase is to rigid energy equation
The energy equation of straight-line segment.
Preferred embodiment, target gridding calculates in the present embodiment, including,
Straight-line segment constraint and Local Phase are added to during target gridding is calculated to rigid constraint, and is employed
The mode for following harm reason is iterated optimization, so as to which target gridding be made more to stablize.Present invention incorporates characteristic point, Local Phases pair
The constraintss such as rigidity and straight-line segment carry out calculating target gridding position, are exactly to minimize energy equation for simplification：
Min | | E | |=min | | α Ef+βEs+γEl||
Wherein, Ef, Es, ElRespectively the energy equation of characteristic point, relative stiffness and straight-line segment, α, beta, gamma are respectively
Its weight parameter.
Further, the characteristic point energy equation：
Wherein, PkIt is characterized target coordinate position a little, VkA little corresponding four mesh vertex coordinates are characterized,It is four
The weight parameter of a grid.In actual treatment, give each characteristic point different weights according to the distance between match point.
Preferred embodiment, Local Phase is to rigid energy equation in the present embodiment：
Es(V1)=| | V1-(V2+u(V3-V2)+v(R90(V3-V2)))||2
For a vertex V1 of arbitrary triangle, exist between other two vertex V2, V3 of triangle with
Co-relation, therefore the energy equation is added as constraints during target gridding vertex position is calculated, it can keep taking
The local relative stiffness of dress.
Preferred embodiment, the energy equation of the present embodiment cathetus line segment：
The detection of straight-line segment has used a kind of line segmentation algorithm (a line segment detector, LSD), should
Algorithm does not need to adjusting parameter, and the testing result of subpixel accuracy, derivation of energy formula can be obtained within the linear time
For：
Wherein, Lb, LcFor two extreme coordinates of line segment, N is the decile hop count of the line segment,For line bisection coordinate bit
Put, in practical solution procedure by Along ent each on line segment by it where four vertex of grid be indicated.
The garment data of reparation is moved on target body image in the present embodiment, is finally worn by preferred embodiment
Side and the human body image of matching migration, including,
The matching relationship between projection human body contour outline and target body profile is used to be taken to drive quadrilateral mesh to realize
Fill shift function：
Division rule quadrilateral mesh；
According to the human joint points of projection and the matching relationship of target body artis, the pairing calculated between profile point is closed
System；
Target gridding apex coordinate is calculated according to the solution procedure that target gridding calculates；
The shift function of garment data is realized by the driving of grid.
The system exposed the false the present embodiment provides a kind of clothes with human body image, match migration, including,
Read module reads the three-dimensional data of model and the shooting image of clothes；
Acquisition module calculates camera projection matrix, and obtains model's projected image；
Garment data is added to projected image, and carries out repair process of exposing the false by processing module, the clothes number repaired
According to；
Generation module, the garment data of reparation is moved on target body image, is finally exposed the false and matched migration
Human body image.
It exposes the false the present embodiment provides a kind of clothes with human body image, match the product migrated, which is characterized in that including being applicable in
In virtual reality, virtual fitting, virtual social, clothes, footwear and accessories and the image of non-genuine exposure body.
Claims (11)
1. a kind of method that clothes expose the false with human body image, match migration, which is characterized in that including,
Read the three-dimensional data of model and the shooting image of clothes；
Camera projection matrix is calculated, and obtains model's projected image；
Garment data is added to projected image, and carries out repair process of exposing the false, the garment data repaired；
The garment data of reparation is moved on target body image, is finally exposed the false and matched the human body image of migration.
2. the method that a kind of clothes as described in claim 1 expose the false with human body image, match migration, which is characterized in that described
The three-dimensional data of model and the two dimensional image of clothes shooting are read, including,
Model is to carry the nude model of scaling board on two hands and the crown respectively, three dimensional point cloud be by it is high-precision can
See that optical scanning rebuilds to obtain；
The two dimensional image of clothes shooting is needed comprising EXIF information (exchangeable image file), while in order to avoid clothes move to
Occur the excessive situation of visual angle, light differential after on new human body image, thus need to limit clothes shooting flow.
3. the method that a kind of clothes as described in claim 1 expose the false with human body image, match migration, which is characterized in that the meter
Camera projection matrix is calculated, and obtains the projected image of entity model, including,
Calculate camera projection matrix：
The purpose for calculating camera projection matrix is to obtain the human body contour outline in shooting figure under clothes, can be analyzed to two squares
The product of battle array：
P=K [R | T]
Wherein, P is camera projection matrix, and K is camera internal reference matrix, and expression-form is
Fx, fy, px, py are respectively X, and focal length and principal point offset in Y-direction can directly be read from the EXIF information of image
It takes, [R | T] it is Camera extrinsic matrix, expression-form is
θ is around X, Y, Z coordinate axis rotation angle, Tx, Ty respectively, and Tz is X respectively, Y, the translational movement of Z coordinate axis；
Match the acquisition of point set and the generation of projected image：
Characteristic point need to be chosen manually on scaling board in three-dimensional point cloud, and the characteristic point of scaling board can be examined by angle point in shooting figure
Survey method extracts, and using OPENGL, (Open Graphics Library open figure to projected image after projection matrix is calculated
Shape library) rendered.
4. the method that a kind of clothes as described in claim 1 expose the false with human body image, match migration, which is characterized in that described
Projected image that garment data is added to, and carry out repair process of exposing the false, the garment data repaired, including,
Mesh generation is searched with match point；
The regular quadrilateral grid of 20*30 is divided into for the image that size is 800*1200, extracts clothes profile respectively first
With human body contour outline point set, and the direction vector of each profile point is calculated；Then, human body contour outline point set is traversed, passes through direction vector
Between angle and the distance between 2 points as criterion, and by the way of one-to-many matching, from clothes profile point
Search matching coordinate points；
Target gridding calculates：
Characteristic point energy equation
Local Phase is to rigid energy equation
The energy equation of straight-line segment.
5. the method that a kind of clothes as claimed in claim 4 expose the false with human body image, match migration, which is characterized in that described
Target gridding calculate, including,
Be added to during target gridding is calculated straight-line segment constraint and Local Phase to rigid constraint, and employ follow it is bad
The mode of processing is iterated optimization, so as to which target gridding be made more to stablize.Present invention incorporates characteristic point, local relative stiffnesses
And the constraintss such as straight-line segment carry out calculating target gridding position,
It is exactly to minimize energy equation for simplifying：
Min | | E | |=min | | α Ef+βEs+γEl||
Wherein, Ef, Es, ElThe respectively energy equation of characteristic point, relative stiffness and straight-line segment, α, beta, gamma are its power respectively
Weight parameter.
6. the method that a kind of clothes as claimed in claim 4 expose the false with human body image, match migration, which is characterized in that feature
Point energy equation：
Wherein, PkIt is characterized target coordinate position a little, VkA little corresponding four mesh vertex coordinates are characterized,For four nets
The weight parameter of lattice.In actual treatment, give each characteristic point different weights according to the distance between match point.
7. the method that a kind of clothes as claimed in claim 4 expose the false with human body image, match migration, which is characterized in that part
Relative stiffness energy equation：
Es(V1)=| | V1-(V2+u(V3-V2)+v(R90(V3-V2)))||2
For a vertex V1 of arbitrary triangle, there is above close between other two vertex V2, V3 of triangle
System, therefore the energy equation is added as constraints during target gridding vertex position is calculated, clothes can be kept
Local relative stiffness.
8. the method that a kind of clothes as claimed in claim 4 expose the false with human body image, match migration, which is characterized in that straight line
The energy equation of line segment：
The detection of straight-line segment has used a kind of line segmentation algorithm (aline segment detector, LSD), and the algorithm is not
Adjusting parameter is needed, and the testing result of subpixel accuracy can be obtained within the linear time, derivation of energy formula is：
Wherein, Lb, LcFor two extreme coordinates of line segment, N is the decile hop count of the line segment,For line bisection coordinate position,
In practical solution procedure by Along ent each on line segment by it where four vertex of grid be indicated.
9. the method that a kind of clothes as described in claim 1 expose the false with human body image, match migration, which is characterized in that will repair
Multiple garment data is moved on target body image, is finally exposed the false and matched the human body image of migration, including,
The matching relationship between projection human body contour outline and target body profile is used to drive quadrilateral mesh to realize that clothes move
Shifting function：
Division rule quadrilateral mesh；
According to the human joint points of projection and the matching relationship of target body artis, the pairing relationship between profile point is calculated；
Target gridding apex coordinate is calculated according to the solution procedure that target gridding calculates；
The shift function of garment data is realized by the driving of grid.
10. a kind of system that clothes expose the false with human body image, match migration, which is characterized in that including,
Read module reads the three-dimensional data of model and the shooting image of clothes；
Acquisition module calculates camera projection matrix, and obtains model's projected image；
Garment data is added to projected image, and carries out repair process of exposing the false by processing module, the garment data repaired；
Generation module, the garment data of reparation is moved on target body image, is finally exposed the false and matched the people of migration
Body image.
The product of migration 11. a kind of clothes are exposed the false with human body image, matched, which is characterized in that including being suitable for virtual reality, void
Intend fitting, virtual social, clothes, footwear and the image of accessories and non-genuine exposure body, which is characterized in that described one kind
It is a kind of clothes described in any one in claims 1 to 10 and people that clothes, which expose the false with human body image, match the product migrated,
Body image exposes the false, matches the method and system migrated.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810034021.3A CN108269271A (en) | 2018-01-15 | 2018-01-15 | A kind of clothes expose the false with human body image, match the method and system migrated |
| CN201810919518.3A CN109934935B (en) | 2018-01-15 | 2018-08-14 | Method and system for wearing and matching migration of clothes and human body images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810034021.3A CN108269271A (en) | 2018-01-15 | 2018-01-15 | A kind of clothes expose the false with human body image, match the method and system migrated |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108269271A true CN108269271A (en) | 2018-07-10 |
Family
ID=62775633
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810034021.3A Withdrawn CN108269271A (en) | 2018-01-15 | 2018-01-15 | A kind of clothes expose the false with human body image, match the method and system migrated |
| CN201810919518.3A Active CN109934935B (en) | 2018-01-15 | 2018-08-14 | Method and system for wearing and matching migration of clothes and human body images |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810919518.3A Active CN109934935B (en) | 2018-01-15 | 2018-08-14 | Method and system for wearing and matching migration of clothes and human body images |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108269271A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008910A (en) * | 2019-04-10 | 2019-07-12 | 江西理工大学 | A kind of movie and television play is exposed the false the detection method of camera lens |
| CN111144478A (en) * | 2019-12-25 | 2020-05-12 | 电子科技大学 | Automatic detection method for through lens |
| CN111178167A (en) * | 2019-12-12 | 2020-05-19 | 咪咕文化科技有限公司 | Method and device for auditing through lens, electronic equipment and storage medium |
| CN111913572A (en) * | 2020-07-03 | 2020-11-10 | 山东大学 | Man-machine interaction system and method for labor transformation of prisoners |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111787242B (en) | 2019-07-17 | 2021-12-07 | 北京京东尚科信息技术有限公司 | Method and apparatus for virtual fitting |
| CN112529670B (en) * | 2021-02-07 | 2021-04-30 | 上海英立视电子有限公司 | Virtual fitting method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070111417A (en) * | 2007-10-04 | 2007-11-21 | 심형용 | Simulation system for clothes ,using projector |
| CN101908231B (en) * | 2010-07-27 | 2012-05-30 | 清华大学 | Reconstruction method and system for processing three-dimensional point cloud containing main plane scene |
| CN103473806B (en) * | 2013-09-23 | 2016-03-16 | 北京航空航天大学 | A kind of clothes 3 D model construction method based on single image |
| CN104700452B (en) * | 2015-03-24 | 2016-03-02 | 中国人民解放军国防科学技术大学 | A kind of 3 D human body attitude mode matching process towards any attitude |
| CN106709947B (en) * | 2016-12-20 | 2020-06-19 | 西安交通大学 | Three-dimensional human body rapid modeling system based on RGBD camera |
-
2018
- 2018-01-15 CN CN201810034021.3A patent/CN108269271A/en not_active Withdrawn
- 2018-08-14 CN CN201810919518.3A patent/CN109934935B/en active Active
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008910A (en) * | 2019-04-10 | 2019-07-12 | 江西理工大学 | A kind of movie and television play is exposed the false the detection method of camera lens |
| CN110008910B (en) * | 2019-04-10 | 2022-01-28 | 江西理工大学 | Detection method for movie and television series cut-to-help lens |
| CN111178167A (en) * | 2019-12-12 | 2020-05-19 | 咪咕文化科技有限公司 | Method and device for auditing through lens, electronic equipment and storage medium |
| CN111178167B (en) * | 2019-12-12 | 2023-07-25 | 咪咕文化科技有限公司 | Method and device for checking lasting lens, electronic equipment and storage medium |
| CN111144478A (en) * | 2019-12-25 | 2020-05-12 | 电子科技大学 | Automatic detection method for through lens |
| CN111144478B (en) * | 2019-12-25 | 2022-06-14 | 电子科技大学 | Automatic detection method for through lens |
| CN111913572A (en) * | 2020-07-03 | 2020-11-10 | 山东大学 | Man-machine interaction system and method for labor transformation of prisoners |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109934935A (en) | 2019-06-25 |
| CN109934935B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108269271A (en) | A kind of clothes expose the false with human body image, match the method and system migrated | |
| CN106289106B (en) | The stereo vision sensor and scaling method that a kind of line-scan digital camera and area array cameras are combined | |
| US6930685B1 (en) | Image processing method and apparatus | |
| CN104778694B (en) | A kind of parametrization automatic geometric correction method shown towards multi-projection system | |
| CN103971404B (en) | 3D real-scene copying device having high cost performance | |
| US5850469A (en) | Real time tracking of camera pose | |
| CN104240289B (en) | Three-dimensional digitalization reconstruction method and system based on single camera | |
| EP1522051B1 (en) | Discrete linear space sampling method and apparatus for generating digital 3d models | |
| CN104335005B (en) | 3D is scanned and alignment system | |
| CN108053476B (en) | Human body parameter measuring system and method based on segmented three-dimensional reconstruction | |
| CN112258390A (en) | High-precision microscopic virtual learning resource generation method | |
| CN110288642A (en) | Three-dimension object fast reconstructing method based on camera array | |
| CN108537879A (en) | Reconstructing three-dimensional model system and method | |
| CN108876926A (en) | Navigation methods and systems, AR/VR client device in a kind of panoramic scene | |
| CN103535960B (en) | Human body three-dimensional measurement method based on digital images | |
| CN107167093A (en) | The combined type measuring system and measuring method of a kind of laser line scanning and shadow Moire | |
| CN107170037A (en) | A kind of real-time three-dimensional point cloud method for reconstructing and system based on multiple-camera | |
| US20090073259A1 (en) | Imaging system and method | |
| CN110312111A (en) | The devices, systems, and methods calibrated automatically for image device | |
| GB2352901A (en) | Rendering three dimensional representations utilising projected light patterns | |
| CN109801365A (en) | A kind of three-dimensional modeling data acquisition device and its three-dimensional modeling method | |
| CN109945841B (en) | Industrial photogrammetry method without coding points | |
| CN110243307A (en) | A kind of automatized three-dimensional colour imaging and measuring system | |
| CN111060006A (en) | Viewpoint planning method based on three-dimensional model | |
| JP2002516443A (en) | Method and apparatus for three-dimensional display |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180710 |