CN109934935A - A kind of clothes are exposed the false with human body image, match the method and system of migration - Google Patents
A kind of clothes are exposed the false with human body image, match the method and system of migration Download PDFInfo
- Publication number
- CN109934935A CN109934935A CN201810919518.3A CN201810919518A CN109934935A CN 109934935 A CN109934935 A CN 109934935A CN 201810919518 A CN201810919518 A CN 201810919518A CN 109934935 A CN109934935 A CN 109934935A
- Authority
- CN
- China
- Prior art keywords
- clothes
- human body
- image
- 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.)
- Granted
Links
- 230000005012 migration Effects 0.000 title claims abstract description 34
- 238000013508 migration Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000011159 matrix material Substances 0.000 claims abstract description 30
- 230000008439 repair process Effects 0.000 claims abstract description 12
- 239000000284 extract Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000009795 derivation Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000009877 rendering Methods 0.000 abstract description 2
- 239000004744 fabric Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
Abstract
A kind of method that the present invention relates to computer graphics and technical field of computer vision more particularly to clothes to expose the false with human body image, matches migration, comprising: 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, the human body image of migration is finally exposed the false and matched.The present invention handles the image of clothing under different shooting environmentals, it is allowed on the human body image being through under different perspectives, using first matching clothes with the human body image of projection and carrying out reparation of exposing the false, the garment data after reparation is then moved into 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 technique
The matching of clothes and human body image migrates, and is exactly before the information such as unobvious change 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 obvious 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, directly cannot directly be matched it with the human body image under same posture, therefore this
Invention solves the migration of the clothes under different shooting environmentals from the matching migrating technology of human body image using a kind of clothes and asks
Topic.
Summary of the invention
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, the human figure of migration is finally exposed the false and matched
Picture.
Further, the two dimensional image of the three-dimensional data of the reading model and clothes shooting, including,
Model is to have 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 needs to shoot process to clothes and limit
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 can be analyzed to two to obtain the human body contour outline in shooting figure under clothes
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
It reads, [R | T] it is Camera extrinsic matrix, expression-form is
θ is around X, Y respectively, and Z coordinate axis rotates angle, and Tx, Ty, Tz is X, Y, the translational movement of Z coordinate axis respectively;
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 calculating projection matrix
Open graphic library) rendered.
Further, described that garment data is added to projected image, and repair process of exposing the false is carried out, it is repaired
Garment data, including,
Grid dividing and match point are searched;
It is divided into the regular quadrilateral grid of 20*30 for the image having a size of 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, direction is passed through
The distance between angle and two o'clock between vector are used as judgment criteria, 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,
It is added to straight-line segment constraint and Local Phase during calculating target gridding to rigid constraint, and uses
The mode for following harm reason is iterated optimization, to keep target gridding more stable.Present invention incorporates characteristic points, Local Phase pair
The constraint conditions 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, between other two vertex V2, V3 of triangle exist with
Co-relation, therefore the energy equation is added as constraint condition during calculating target gridding vertex position, 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 adjusting parameter, and the testing result of subpixel accuracy, derivation of energy formula can be obtained within the linear time
Are as follows:
Wherein, Lb, LcFor two extreme coordinates of line segment, N is the equal part number of segment of the line segment,For line bisection coordinate bit
Set, 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 drive quadrilateral mesh to realize clothes
Fill shift function:
Division rule quadrilateral mesh;
According to the matching relationship of the human joint points of projection and 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 a kind of system that 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;
Module is obtained, calculates camera projection matrix, and obtain 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, shoes and accessories and non-genuine exposure body.
Beneficial effect
The invention proposes a kind of clothes to expose the false with human body image, matches the method and system of migration, by different shooting rings
Image of clothing under border is handled, and is allowed on the human body image being through under different perspectives.By shooting angle, shooting distance, at
As the influence of the parameters such as camera lens and size, the style difference of different garment increase and keep its line in clothes transition process
Reason, the difficulty of profile, therefore use and clothes are matched with the human body image of projection first and carry out reparation of exposing the false, then it will repair again
Garment data after multiple moves to the matching migration function that the mode on the human body image of final rendering realizes clothes and human body image
Energy.
Specific embodiment
A kind of method that the present embodiment provides clothes to expose the false with human body image, matches 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, the human figure of migration is finally exposed the false and matched
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 have 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 needs to shoot process to clothes and limit
System.
Clothes shooting:
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 far as possible.
Pedestal is first well placed by model, then places model;The clothes for needing to shoot are put on, scaling board is installed.
Guarantee 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, camera at a distance from vertical corresponding points and model's bottom plate is 255 centimetres with ground.
Camera debugging 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 can be analyzed to two to obtain the human body contour outline in shooting figure under clothes
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
It reads, [R | T] it is Camera extrinsic matrix, expression-form is
θ is around X, Y respectively, and Z coordinate axis rotates angle, and Tx, Ty, Tz is X, Y, the translational movement of Z coordinate axis respectively;
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 calculating projection matrix
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,
Grid dividing and match point are searched;
It is divided into the regular quadrilateral grid of 20*30 for the image having a size of 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, direction is passed through
The distance between angle and two o'clock between vector are used as judgment criteria, 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,
It is added to straight-line segment constraint and Local Phase during calculating target gridding to rigid constraint, and uses
The mode for following harm reason is iterated optimization, to keep target gridding more stable.Present invention incorporates characteristic points, Local Phase pair
The constraint conditions 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, between other two vertex V2, V3 of triangle exist with
Co-relation, therefore the energy equation is added as constraint condition during calculating target gridding vertex position, it can keep taking
The local relative stiffness of dress.
Preferred embodiment, the energy equation of straight-line segment in the present embodiment:
The detection of straight-line segment has used a kind of line segmentation algorithm (a line segment detector, LSD), should
Algorithm does not need adjusting parameter, and the testing result of subpixel accuracy, derivation of energy formula can be obtained within the linear time
Are as follows:
Wherein, Lb, LcFor two extreme coordinates of line segment, N is the equal part number of segment of the line segment,For line bisection coordinate bit
Set, 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
The human body image of side and matching migration, including,
The matching relationship between projection human body contour outline and target body profile is used to drive quadrilateral mesh to realize clothes
Fill shift function:
Division rule quadrilateral mesh;
According to the matching relationship of the human joint points of projection and 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 that the present embodiment provides a kind of clothes to expose the false with human body image, matches migration, including,
Read module reads the three-dimensional data of model and the shooting image of clothes;
Module is obtained, calculates camera projection matrix, and obtain 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 embodiment provides a kind of clothes to expose the false with human body image, matches the product of migration, which is characterized in that including being applicable in
In virtual reality, virtual fitting, virtual social, clothes, shoes 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, the human body image of migration is finally exposed the false and matched.
2. a kind of method that clothes expose the false with human body image, match migration as described in claim 1, 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 have a nude model of scaling board on two hands and the crown respectively, three dimensional point cloud be by it is high-precision can
Light-exposed scan rebuilding obtains;
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 needs to shoot process to clothes and limit.
3. a kind of method that clothes expose the false with human body image, match migration as described in claim 1, 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 can be analyzed to two squares to obtain the human body contour outline in shooting figure under clothes
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, 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 respectively, and Z coordinate axis rotates angle, and Tx, Ty, Tz is X, Y, the translational movement of Z coordinate axis respectively;
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 projected image uses OPENGL (the open figure of Open Graphics Library after calculating projection matrix
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,
Grid dividing and match point are searched;
It is divided into the regular quadrilateral grid of 20*30 for the image having a size of 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, direction vector is passed through
Between angle and the distance between two o'clock be used as judgment criteria, 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,
Straight-line segment constraint and Local Phase are added to during calculating target gridding to rigid constraint, and bad using following
The mode of processing is iterated optimization, to keep target gridding more stable.Present invention incorporates characteristic points, local relative stiffness
And the constraint conditions such as 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, 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 constraint condition during calculating target gridding vertex position, 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 (a line segment detector, LSD), the algorithm
Adjusting parameter is not needed, and can obtain the testing result of subpixel accuracy, derivation of energy formula within the linear time are as follows:
Wherein, Lb, LcFor two extreme coordinates of line segment, N is the equal part number of segment 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 moves 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 matching relationship of the human joint points of projection and 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. the system that a kind of 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;
Module is obtained, calculates camera projection matrix, and obtain 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
Quasi- fitting, virtual social, clothes, shoes and accessories and non-genuine exposure body image, which is characterized in that described one kind
Clothes expose the false with human body image, match the product of migration as a kind of clothes and people described in any one of claims 1 to 10
Body image exposes the false, matches the method and system migrated.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2018100340213 | 2018-01-15 | ||
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 (2)
Publication Number | Publication Date |
---|---|
CN109934935A true CN109934935A (en) | 2019-06-25 |
CN109934935B CN109934935B (en) | 2022-10-21 |
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 Before (1)
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 |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN108269271A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111787242A (en) * | 2019-07-17 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Method and apparatus for virtual fitting |
CN112529670A (en) * | 2021-02-07 | 2021-03-19 | 上海英立视电子有限公司 | Virtual fitting method |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
CN111144478B (en) * | 2019-12-25 | 2022-06-14 | 电子科技大学 | Automatic detection method for through lens |
CN111913572B (en) * | 2020-07-03 | 2022-03-15 | 山东大学 | Human-computer interaction system and method for user labor learning |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070111417A (en) * | 2007-10-04 | 2007-11-21 | 심형용 | Simulation system for clothes ,using projector |
CN101908231A (en) * | 2010-07-27 | 2010-12-08 | 清华大学 | Reconstruction method and system for processing three-dimensional point cloud containing main plane scene |
CN103473806A (en) * | 2013-09-23 | 2013-12-25 | 北京航空航天大学 | Method for building clothing three-dimensional model based on single image |
CN104700452A (en) * | 2015-03-24 | 2015-06-10 | 中国人民解放军国防科学技术大学 | Three-dimensional body posture model matching method for any posture |
CN106709947A (en) * | 2016-12-20 | 2017-05-24 | 西安交通大学 | RGBD camera-based three-dimensional human body rapid modeling system |
-
2018
- 2018-01-15 CN CN201810034021.3A patent/CN108269271A/en not_active Withdrawn
- 2018-08-14 CN CN201810919518.3A patent/CN109934935B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070111417A (en) * | 2007-10-04 | 2007-11-21 | 심형용 | Simulation system for clothes ,using projector |
CN101908231A (en) * | 2010-07-27 | 2010-12-08 | 清华大学 | Reconstruction method and system for processing three-dimensional point cloud containing main plane scene |
CN103473806A (en) * | 2013-09-23 | 2013-12-25 | 北京航空航天大学 | Method for building clothing three-dimensional model based on single image |
CN104700452A (en) * | 2015-03-24 | 2015-06-10 | 中国人民解放军国防科学技术大学 | Three-dimensional body posture model matching method for any posture |
CN106709947A (en) * | 2016-12-20 | 2017-05-24 | 西安交通大学 | RGBD camera-based three-dimensional human body rapid modeling system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111787242A (en) * | 2019-07-17 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Method and apparatus for virtual fitting |
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 |
US11935167B2 (en) | 2019-07-17 | 2024-03-19 | Reling Jingdong Shangke Information Technology Co., Ltd. | Method and apparatus for virtual fitting |
CN112529670A (en) * | 2021-02-07 | 2021-03-19 | 上海英立视电子有限公司 | Virtual fitting method |
CN112529670B (en) * | 2021-02-07 | 2021-04-30 | 上海英立视电子有限公司 | Virtual fitting method |
Also Published As
Publication number | Publication date |
---|---|
CN109934935B (en) | 2022-10-21 |
CN108269271A (en) | 2018-07-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109934935A (en) | A kind of clothes are exposed the false with human body image, match the method and system of migration | |
CN106595528B (en) | A kind of micro- binocular stereo vision measurement method of telecentricity based on digital speckle | |
CN106780619B (en) | Human body size measuring method based on Kinect depth camera | |
CN104240289B (en) | Three-dimensional digitalization reconstruction method and system based on single camera | |
CN104335005B (en) | 3D is scanned and alignment system | |
US6930685B1 (en) | Image processing method and apparatus | |
KR20200087757A (en) | Full convolutional point of interest detection and description through homographic adaptation | |
CN106056620B (en) | Line laser camera measurement system calibrating method | |
CN108765548A (en) | Three-dimensional scenic real-time reconstruction method based on depth camera | |
CN112258390A (en) | High-precision microscopic virtual learning resource generation method | |
CN108537879A (en) | Reconstructing three-dimensional model system and method | |
CN107590708B (en) | Method and device for generating user specific body shape model | |
KR20130138247A (en) | Rapid 3d modeling | |
CN103196370A (en) | Measuring method and measuring device of conduit connector space pose parameters | |
EP1522051A2 (en) | Discrete linear space sampling method and apparatus for generating digital 3d models | |
CN109556535B (en) | Three-dimensional surface type one-step reconstruction method based on color fringe projection | |
CN109801365A (en) | A kind of three-dimensional modeling data acquisition device and its three-dimensional modeling method | |
CN107167093A (en) | The combined type measuring system and measuring method of a kind of laser line scanning and shadow Moire | |
EP3382645B1 (en) | Method for generation of a 3d model based on structure from motion and photometric stereo of 2d sparse images | |
JP2009081853A (en) | Imaging system and method | |
CN110312111A (en) | The devices, systems, and methods calibrated automatically for image device | |
CN109341527A (en) | A kind of the structured light projection three-dimension measuring system and method for auto shadows compensation | |
CN111060006A (en) | Viewpoint planning method based on three-dimensional model | |
CN109242898A (en) | A kind of three-dimensional modeling method and system based on image sequence | |
CN108399634A (en) | The RGB-D data creation methods and device calculated based on high in the clouds |
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: 20231128 Address after: Gao Lou Zhen Hong Di Cun, Rui'an City, Wenzhou City, Zhejiang Province, 325200 Patentee after: Wang Conghai Address before: 518000 floor 10, Yihua financial technology building, 2388 Houhai Avenue, Nanshan District, Shenzhen, Guangdong Patentee before: SHENZHEN CLOUDREAM INFORMATION TECHNOLOGY CO.,LTD. |