CN110175897A - A kind of 3D synthesis fitting method and system - Google Patents
A kind of 3D synthesis fitting method and system Download PDFInfo
- Publication number
- CN110175897A CN110175897A CN201910475274.9A CN201910475274A CN110175897A CN 110175897 A CN110175897 A CN 110175897A CN 201910475274 A CN201910475274 A CN 201910475274A CN 110175897 A CN110175897 A CN 110175897A
- Authority
- CN
- China
- Prior art keywords
- model
- module
- clothes
- dimensional
- vertex
- 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- Withdrawn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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- 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
Abstract
The present invention discloses a kind of 3D synthesis fitting method and system, comprising the following steps: 1) obtains two photos of clothes;2) contour line and key node of clothes photo are identified;3) it calculates the identical match point of two photos to be fitted, generates the garment virtual threedimensional model of base edition type;4) depth map shooting is carried out to human body, to obtain individual depth image;5) individual depth image is transformed to three-dimensional point cloud, and obtains the matching double points between the three-dimensional point cloud and reconstruction model vertex and parameterized human body model vertex;6) energy function is established according to matching double points, and solves the non-rigid motion evolution parameter and parametric human body posture model parameter on each vertex on reconstruction model jointly;7) energy function is solved;This can conveniently experience fitting based on the 3D composograph that body data and clothes data generate.
Description
Technical field
The present invention is 3D rendering applied technical field, relates generally to a kind of 3D synthesis fitting method and system.
Background technique
Wearing the clothes, it is suitable to be not only particular about, and more exquisite quality, it is that customer directly goes to market to select that traditional fitting method is most common
The examination of the clothes oneself liked then piecemeal is selected, not only time-consuming in this way, people is more easily tired out.Clothing is liked in online selection
Clothes, can only provide general conventional parameter, then buy back and come for a fitting, and may be because parameter inaccuracy, or misfit and also need to move back
Goods can bring great inconvenience in this way.Fitting can be conveniently experienced by the mobile terminal device of people, reduces and returns goods
Rate becomes a technical problem to be solved urgently.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of to generate 3D composite diagram based on body data and clothes data
Picture can conveniently experience fitting.
To solve the above problems, the present invention adopts the following technical scheme:
A kind of 3D synthesis fitting method, comprising the following steps:
1) two photos of clothes are obtained;
2) contour line and key node of clothes photo are identified;
3) it calculates the identical match point of two photos to be fitted, generates the garment virtual threedimensional model of base edition type;
4) depth map shooting is carried out to human body, to obtain individual depth image;
5) individual depth image is transformed to three-dimensional point cloud, and obtains the three-dimensional point cloud and reconstruction model vertex and parameter
Change the matching double points between manikin vertex;
6) energy function is established according to matching double points, and solves the non-rigid motion on each vertex on reconstruction model jointly
Evolution parameter and parametric human body posture model parameter;
7) energy function is solved, and is aligned reconstruction model with three-dimensional point cloud according to solving result;
8) model after being aligned with completion is updated by depth map, to carry out real-time body's dynamic three-dimensional reconstruction;
9) using picture mobile tool that human 3d model and garment virtual is three-dimensional in two-dimensional coordinate (y, z) plane
Model Matching, in two-dimensional coordinate (y, z) plane, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
Preferably, two photos are respectively that front is shone according to the back side in the step 1).
It is fitted preferably, calculating identical match point in two photos based on curve in the step 3).
Preferably, the curve is bezier curve.
Preferably, the step 2) further includes whether the contour line of inspection clothes photo and key node have deviation, if
There are then artificial minitrim wheel profile and key node.
The present invention also provides a kind of 3D to synthesize dressing system: including
Clothes photographing module, for obtaining the photo of clothes;
Clothes photo array adjusts module, connect with clothes photographing module, for identification the contour line of clothes photo and pass
Key node;
Garment data computing module calculates the identical match point of two photos and is fitted, and generates the clothes of base edition type
Virtual three-dimensional model;
Human depth's shooting module, for carrying out depth map shooting to human body, to obtain individual depth image;
Transformation Matching module is connect with human depth's shooting module, individual depth image is transformed to three-dimensional point cloud, and obtain
Take the matching double points between the three-dimensional point cloud and reconstruction model vertex and parameterized human body model vertex;
Function establishes module, connect with Transformation Matching module, establishes energy function according to matching double points, and solves weight jointly
The non-rigid motion evolution parameter on each vertex and parametric human body posture model parameter on established model;
Parsing module, and function are established module connection, are solved to the energy function, and will be weighed according to solving result
Established model is aligned with three-dimensional point cloud;
Completion module is updated, is connect with parsing module, for depth map to be updated to the model after being aligned with completion, to carry out
Real-time body's dynamic three-dimensional reconstruction;
Covering treatment module is connect, at two-dimensional coordinate (y, z) with garment data computing module and update completion module
In plane, human 3d model is matched with garment virtual threedimensional model using picture mobile tool, it is flat at two-dimensional coordinate (y, z)
In face, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
The invention has the benefit that after establishing threedimensional model to human body and clothes respectively, by clothing by the way of covering
Model and manikin fitting are taken, not only can achieve the effect tried on, simultaneously synthesizing fast speed, usage experience is good.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow chart that a kind of 3D of embodiment 1 synthesizes fitting method.
Fig. 2 is the flow chart that a kind of 3D of embodiment 2 synthesizes fitting method.
Fig. 3 is the connection block diagram that a kind of 3D of the invention synthesizes dressing system.
In figure:
1, clothes photographing module;2, clothes photo array adjusts module;3, garment data computing module;4, human depth claps
Take the photograph module;5, Transformation Matching module;6, function establishes module;7, parsing module;8, completion module is updated;9, covering treatment mould
Block.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
Embodiment 1
As shown in Figure 1, a kind of 3D synthesizes fitting method, comprising the following steps:
1) two photos of clothes are obtained;
2) contour line and key node of clothes photo are identified;
3) it calculates the identical match point of two photos to be fitted, generates the garment virtual threedimensional model of base edition type;
4) depth map shooting is carried out to human body, to obtain individual depth image;
5) individual depth image is transformed to three-dimensional point cloud, and obtains the three-dimensional point cloud and reconstruction model vertex and parameter
Change the matching double points between manikin vertex;
6) energy function is established according to matching double points, and solves the non-rigid motion on each vertex on reconstruction model jointly
Evolution parameter and parametric human body posture model parameter;
7) energy function is solved, and is aligned reconstruction model with three-dimensional point cloud according to solving result;
8) model after being aligned with completion is updated by depth map, to carry out real-time body's dynamic three-dimensional reconstruction;
9) using picture mobile tool that human 3d model and garment virtual is three-dimensional in two-dimensional coordinate (y, z) plane
Model Matching, in two-dimensional coordinate (y, z) plane, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
Embodiment 2
1) two photos of clothes are obtained;
2) contour line and key node of clothes photo are identified;
3) it calculates the identical match point of two photos to be fitted, generates the garment virtual threedimensional model of base edition type;
4) depth map shooting is carried out to human body, to obtain individual depth image;
5) individual depth image is transformed to three-dimensional point cloud, and obtains the three-dimensional point cloud and reconstruction model vertex and parameter
Change the matching double points between manikin vertex;
6) energy function is established according to matching double points, and solves the non-rigid motion on each vertex on reconstruction model jointly
Evolution parameter and parametric human body posture model parameter;
7) energy function is solved, and is aligned reconstruction model with three-dimensional point cloud according to solving result;
8) model after being aligned with completion is updated by depth map, to carry out real-time body's dynamic three-dimensional reconstruction;
9) using picture mobile tool that human 3d model and garment virtual is three-dimensional in two-dimensional coordinate (y, z) plane
Model Matching, in two-dimensional coordinate (y, z) plane, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
Preferably, two photos are respectively that front is shone according to the back side in the step 1).
In the present embodiment, identical match point in two photos is calculated based on curve in the step 3) to be fitted.
In the present embodiment, the curve is bezier curve.
In the present embodiment, the step 2) further includes checking whether the contour line of clothes photo and key node have partially
Difference, artificial minitrim wheel profile and key node if having.
The present invention also provides a kind of 3D to synthesize dressing system: including
Clothes photographing module 1, for obtaining the photo of clothes;
Clothes photo array adjusts module 2, connect with clothes photographing module, for identification the contour line of clothes photo and pass
Key node;
Garment data computing module 3 calculates the identical match point of two photos and is fitted, and generates the clothes of base edition type
Virtual three-dimensional model;
Human depth's shooting module 4, for carrying out depth map shooting to human body, to obtain individual depth image;
Transformation Matching module 5 is connect with human depth's shooting module, individual depth image is transformed to three-dimensional point cloud, and
Obtain the matching double points between the three-dimensional point cloud and reconstruction model vertex and parameterized human body model vertex;
Function establishes module 6, connect with Transformation Matching module, establishes energy function according to matching double points, and solve jointly
The non-rigid motion evolution parameter on each vertex and parametric human body posture model parameter on reconstruction model;
Parsing module 7, and function are established module connection, are solved to the energy function, and will according to solving result
Reconstruction model is aligned with three-dimensional point cloud;
Update completion module 8, connect with parsing module, for by depth map update and completion be aligned after model, with into
Row real-time body's dynamic three-dimensional reconstruction;
Covering treatment module 9, with garment data computing module and update completion module connect, be used for two-dimensional coordinate (y,
Z) in plane, human 3d model is matched with garment virtual threedimensional model using picture mobile tool, at two-dimensional coordinate (y, z)
In plane, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
The invention has the benefit that after establishing threedimensional model to human body and clothes respectively, by clothing by the way of covering
Model and manikin fitting are taken, not only can achieve the effect tried on, simultaneously synthesizing fast speed, usage experience is good.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
The change or replacement expected without creative work, should be covered by the protection scope of the present invention.
Claims (6)
1. a kind of 3D synthesizes fitting method, it is characterised in that: the following steps are included:
1) two photos of clothes are obtained;
2) contour line and key node of clothes photo are identified;
3) it calculates the identical match point of two photos to be fitted, generates the garment virtual threedimensional model of base edition type;
4) depth map shooting is carried out to human body, to obtain individual depth image;
5) individual depth image is transformed to three-dimensional point cloud, and obtains the three-dimensional point cloud and reconstruction model vertex and parametrization people
Matching double points between body Model vertex;
6) energy function is established according to matching double points, and solves the non-rigid motion position on each vertex on reconstruction model jointly
Transformation parameter and parametric human body posture model parameter;
7) energy function is solved, and is aligned reconstruction model with three-dimensional point cloud according to solving result;
8) model after being aligned with completion is updated by depth map, to carry out real-time body's dynamic three-dimensional reconstruction;
9) in two-dimensional coordinate (y, z) plane, tool is moved by human 3d model and garment virtual threedimensional model using picture
Matching, in two-dimensional coordinate (y, z) plane, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
2. 3D according to claim 1 synthesizes fitting method, it is characterised in that: two photos are respectively in the step 1)
Front is shone according to the back side.
3. 3D according to claim 2 synthesizes fitting method, it is characterised in that: calculate two based on curve in the step 3)
Identical match point in photo is opened to be fitted.
4. 3D according to claim 3 synthesizes fitting method, it is characterised in that: the curve is bezier curve.
5. 3D according to claim 4 synthesizes fitting method, it is characterised in that: the step 2) further includes checking that clothes shine
Whether the contour line and key node of piece have deviation, artificial minitrim wheel profile and key node if having.
6. a kind of 3D synthesizes dressing system, it is characterised in that: including
Clothes photographing module, for obtaining the photo of clothes;
Clothes photo array adjusts module, connect with clothes photographing module, for identification the contour line of clothes photo and crucial section
Point;
Garment data computing module calculates the identical match point of two photos and is fitted, and generates the garment virtual of base edition type
Threedimensional model;
Human depth's shooting module, for carrying out depth map shooting to human body, to obtain individual depth image;
Transformation Matching module is connect with human depth's shooting module, individual depth image is transformed to three-dimensional point cloud, and obtain institute
State the matching double points between three-dimensional point cloud and reconstruction model vertex and parameterized human body model vertex;
Function establishes module, connect with Transformation Matching module, establishes energy function according to matching double points, and solves jointly and rebuild mould
The non-rigid motion evolution parameter on each vertex and parametric human body posture model parameter in type;
Parsing module, and function are established module connection, are solved to the energy function, and will rebuild mould according to solving result
Type is aligned with three-dimensional point cloud;
Completion module is updated, is connect with parsing module, it is real-time to carry out for depth map to be updated to the model after being aligned with completion
Human body dynamic three-dimensional reconstruction;
Covering treatment module is connect, in two-dimensional coordinate (y, z) plane with garment data computing module and update completion module
It is interior, human 3d model is matched with garment virtual threedimensional model using picture mobile tool, in two-dimensional coordinate (y, z) plane
Interior, movable clothes virtual three-dimensional model makes it that manikin be completely covered.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910475274.9A CN110175897A (en) | 2019-06-03 | 2019-06-03 | A kind of 3D synthesis fitting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910475274.9A CN110175897A (en) | 2019-06-03 | 2019-06-03 | A kind of 3D synthesis fitting method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110175897A true CN110175897A (en) | 2019-08-27 |
Family
ID=67697688
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910475274.9A Withdrawn CN110175897A (en) | 2019-06-03 | 2019-06-03 | A kind of 3D synthesis fitting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110175897A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110706359A (en) * | 2019-09-30 | 2020-01-17 | 恒信东方文化股份有限公司 | Image fitting correction method and system |
CN111950139A (en) * | 2020-07-29 | 2020-11-17 | 日播时尚集团股份有限公司 | Garment grading method and terminal based on objective function optimization |
CN112182682A (en) * | 2020-11-03 | 2021-01-05 | 北京服装学院 | Sports garment type generation method and system |
CN112308673A (en) * | 2020-11-03 | 2021-02-02 | 恒信东方文化股份有限公司 | Modeling method and system of 3D garment shooting tool |
CN112365589A (en) * | 2020-12-01 | 2021-02-12 | 东方梦幻虚拟现实科技有限公司 | Virtual three-dimensional scene display method, device and system |
CN112401369A (en) * | 2020-11-23 | 2021-02-26 | 叠境数字科技(上海)有限公司 | Body parameter measuring method, system, equipment, chip and medium based on human body reconstruction |
CN112884638A (en) * | 2021-02-02 | 2021-06-01 | 北京东方国信科技股份有限公司 | Virtual fitting method and device |
CN112950788A (en) * | 2021-03-22 | 2021-06-11 | 江南大学 | Human body reconstruction and garment customization data acquisition method based on single image |
CN113096249A (en) * | 2021-03-30 | 2021-07-09 | Oppo广东移动通信有限公司 | Method for training vertex reconstruction model, image reconstruction method and electronic equipment |
CN115761143A (en) * | 2022-12-07 | 2023-03-07 | 武汉纺织大学 | 3D virtual reloading model generation method and device based on 2D image |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2852935A1 (en) * | 2012-05-23 | 2015-04-01 | Glasses.Com Inc. | Systems and methods for generating a 3-d model of a user for a virtual try-on product |
CN104637084A (en) * | 2015-01-29 | 2015-05-20 | 吴宇晖 | Method for building garment virtual three-dimensional model and virtual garment trying-on system |
CN108665537A (en) * | 2018-05-15 | 2018-10-16 | 清华大学 | The three-dimensional rebuilding method and system of combined optimization human body figure and display model |
CN109064386A (en) * | 2018-07-23 | 2018-12-21 | 西安建筑科技大学 | A kind of method for building up of 3 D stereo garment form |
-
2019
- 2019-06-03 CN CN201910475274.9A patent/CN110175897A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2852935A1 (en) * | 2012-05-23 | 2015-04-01 | Glasses.Com Inc. | Systems and methods for generating a 3-d model of a user for a virtual try-on product |
CN104637084A (en) * | 2015-01-29 | 2015-05-20 | 吴宇晖 | Method for building garment virtual three-dimensional model and virtual garment trying-on system |
CN108665537A (en) * | 2018-05-15 | 2018-10-16 | 清华大学 | The three-dimensional rebuilding method and system of combined optimization human body figure and display model |
CN109064386A (en) * | 2018-07-23 | 2018-12-21 | 西安建筑科技大学 | A kind of method for building up of 3 D stereo garment form |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110706359A (en) * | 2019-09-30 | 2020-01-17 | 恒信东方文化股份有限公司 | Image fitting correction method and system |
CN111950139B (en) * | 2020-07-29 | 2023-02-28 | 日播时尚集团股份有限公司 | Garment grading method and terminal based on objective function optimization |
CN111950139A (en) * | 2020-07-29 | 2020-11-17 | 日播时尚集团股份有限公司 | Garment grading method and terminal based on objective function optimization |
CN112182682A (en) * | 2020-11-03 | 2021-01-05 | 北京服装学院 | Sports garment type generation method and system |
CN112308673A (en) * | 2020-11-03 | 2021-02-02 | 恒信东方文化股份有限公司 | Modeling method and system of 3D garment shooting tool |
CN112182682B (en) * | 2020-11-03 | 2023-10-13 | 北京服装学院 | Sportswear model generation method and sportswear model generation system |
CN112401369A (en) * | 2020-11-23 | 2021-02-26 | 叠境数字科技(上海)有限公司 | Body parameter measuring method, system, equipment, chip and medium based on human body reconstruction |
CN112365589A (en) * | 2020-12-01 | 2021-02-12 | 东方梦幻虚拟现实科技有限公司 | Virtual three-dimensional scene display method, device and system |
CN112884638A (en) * | 2021-02-02 | 2021-06-01 | 北京东方国信科技股份有限公司 | Virtual fitting method and device |
CN112950788B (en) * | 2021-03-22 | 2022-07-19 | 江南大学 | Human body reconstruction and garment customization data acquisition method based on single image |
CN112950788A (en) * | 2021-03-22 | 2021-06-11 | 江南大学 | Human body reconstruction and garment customization data acquisition method based on single image |
CN113096249B (en) * | 2021-03-30 | 2023-02-17 | Oppo广东移动通信有限公司 | Method for training vertex reconstruction model, image reconstruction method and electronic equipment |
CN113096249A (en) * | 2021-03-30 | 2021-07-09 | Oppo广东移动通信有限公司 | Method for training vertex reconstruction model, image reconstruction method and electronic equipment |
CN115761143A (en) * | 2022-12-07 | 2023-03-07 | 武汉纺织大学 | 3D virtual reloading model generation method and device based on 2D image |
CN115761143B (en) * | 2022-12-07 | 2023-09-19 | 武汉纺织大学 | 3D virtual reloading model generation method and device based on 2D image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110175897A (en) | A kind of 3D synthesis fitting method and system | |
CN108648053A (en) | A kind of imaging method for virtual fitting | |
CN104008557B (en) | A kind of three-dimensional matching process of clothing and anthropometric dummy | |
US20170156430A1 (en) | Method for virtually selecting clothing | |
CN104794722A (en) | Dressed human body three-dimensional bare body model calculation method through single Kinect | |
US20130170715A1 (en) | Garment modeling simulation system and process | |
CN111932678B (en) | Multi-view real-time human motion, gesture, expression and texture reconstruction system | |
CN110335343A (en) | Based on RGBD single-view image human body three-dimensional method for reconstructing and device | |
CN103324860A (en) | Intelligent integrated costume designing and fitting system | |
WO2016173073A1 (en) | Three-dimensional modelling method and device based on dual camera | |
CN107680167A (en) | A kind of three-dimensional (3 D) manikin creation method and system based on user image | |
CN114119907A (en) | Fitting method and device of human body model and storage medium | |
CN102902868A (en) | Three-dimensional simulated clothes fitting system applied to network | |
CN114119905A (en) | Virtual fitting method, system, equipment and storage medium | |
CN107590708A (en) | A kind of method and apparatus for generating the specific bodily form model of user | |
CN104318000A (en) | Automatic generating method of ready-made garment | |
CN114119906A (en) | Self-adaptive driving method and device for clothing model and storage medium | |
CN109118455B (en) | Ancient human skull craniofacial interactive restoration method based on modern soft tissue distribution | |
CN114119910A (en) | Method, equipment and storage medium for matching clothing model with human body model | |
CN109064386A (en) | A kind of method for building up of 3 D stereo garment form | |
CN108846892A (en) | The determination method and device of manikin | |
CN106773050A (en) | A kind of intelligent AR glasses virtually integrated based on two dimensional image | |
Liu et al. | A mixed human body modeling method based on 3D body scanning for clothing industry | |
CN112785723B (en) | Automatic garment modeling method based on two-dimensional garment image and three-dimensional human body model | |
KR101158453B1 (en) | Apparatus and Method for coordinating a simulated clothes with the three dimensional effect at plane using the two dimensions image data |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190827 |
|
WW01 | Invention patent application withdrawn after publication |