CN104680574A - Method for automatically generating 3D face according to photo - Google Patents
Method for automatically generating 3D face according to photo Download PDFInfo
- Publication number
- CN104680574A CN104680574A CN201310607202.8A CN201310607202A CN104680574A CN 104680574 A CN104680574 A CN 104680574A CN 201310607202 A CN201310607202 A CN 201310607202A CN 104680574 A CN104680574 A CN 104680574A
- Authority
- CN
- China
- Prior art keywords
- face
- photo
- automatically generating
- face image
- method automatically
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention relates to a method for automatically generating a 3D face according to a photo. The method is characterized by comprising the following steps: a face material needing to be processed is chosen by a user to generate a 3D face image; then, adjustment, matching and detail modification are performed on the 3D face image; and finally, animated facial expressions are imported into the 3D face image and stored. Thus, a 3D face image can be generated for a user step by step by use of a photo, and the details of each part can be adjusted after generation. The method can cooperate with subsequent procedures, a generated face has a variety of preset facial expressions, and effective 3D face image interaction can be performed. Moreover, the whole generation process is simple and easy to process, the data burden on processing equipment is not increased, and the method is easy for users to operate independently.
Description
Technical field
The present invention relates to a kind of method generating 3D face, particularly relate to a kind of method automatically generating 3D face according to photo.
Background technology
Traditional face reconstruction techniques often uses one or more two dimensional images (such as digital photos) of face to create a three-dimensional statement of face.The statement created according to this can be the file of the personal feature representing different face, such as e-file.Described file may be used for, such as face recognition, the making of animation or play up.
This image, once be acquired, looks it is the basic enterprising row relax of what kind of supposition with regard to frequent at prior knowledge or face usually.This knowledge is often called as " domain knowledge ", a kind of " prior model ", or especially a kind of " Generic face ".Such as, Prior face knowledge can show different types of facial characteristics, the current location of such as eyes, nose etc. or possible position.Prior face knowledge is by supposing that face is by the basic configuration of face and outward appearance, camera parameter, optical parameter and other known elements, or a kind of linear combination of being easy to the element etc. estimated is formed.These elements can be combined the appearance estimating that face is possible.In addition, the domain knowledge Generic face shape that can be defined by artist or the form of average face shape that calculated by multiple known face participate in.
In the process of whole reconstruction, the ordinary skill of human face rebuilding utilizes the prior knowledge of Generic face, and possible lineup's face is measured or deformation parameter.Another common technology attempts the use avoiding Prior face knowledge, but uses the method for pure data-driven to realize human face rebuilding.This can realize, and such as, utilizes the triangulation from the two-dimentional main points multiple images that multiple calibrated cameras obtains.Unfortunately, owing to make use of Generic face in whole process of reconstruction, the former method may provide unpractical data.The method of the latter needs extra hardware construction, and this hardware construction is in fact difficult to realize under a rational cost.The method of the pure data-driven of single camera alleviates the hardware constraints of various visual angles stereoscopic approach, but it self may owing to lacking constraint and unstable in the stage of process.
But existing mode is all reappear based on the genuine face of plan, and implementation process is too complicated, is unfavorable for the fast and convenient realization of user, can not effectively be combined with existing pictures, carries out DIY coupling and arranges.
Summary of the invention
Object of the present invention is exactly to solve the above-mentioned problems in the prior art, provides a kind of method automatically generating 3D face according to photo.
Object of the present invention is achieved through the following technical solutions:
Automatically generate a method for 3D face according to photo, it comprises the following steps: 1., user selects to need face material to be processed step, generates 3D face image; 2., adjustment coupling 3D face is vivid for step; 3. step, is carried out 3D face image details and is modified; 4. full animation expression, is imported 3D face image by step, forms 3D face image finished product; 5. step, preserves 3D face image finished product.
A kind of above-mentioned method automatically generating 3D face according to photo, wherein: the picture file that the 1. described face material of step provides for user, or to take pictures the human face photo of acquisition for user.
Further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: described picture file is cartoon figure, or is portrait photo.
Further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: the 2. described adjustment matching content of step comprises, face size, eye position, nose position, face position.
Further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: described eye position comprises eyebrow distribution and eyes opening and closing scope, and described face position comprises face opening and closing scope.
Further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: the 3D face image details that step is 3. described, comprises eye color, eyes size, hair hair style, hair color, head decoration.
Further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: described head decoration comprises eye shadow, cap, earphone, beard, earrings.
Further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: the 4. described full animation expression of step comprises smile, laughs, opens one's eyes, closes one's eyes, opens one's mouth, shuts up, crys.
Again further, a kind of above-mentioned method automatically generating 3D face according to photo, wherein: the 5. described 3D face image finished product of step is kept at processing locality end, or is kept at high in the clouds.
The advantage of technical solution of the present invention is mainly reflected in: utilize a photo, helps user to generate 3D face image step by step, can adjust the details of various piece after generation.Thereby, it is possible to coordinate with down-stream, the face of generation has prefabricated various expressions, carries out effective 3D face image interactive.Further, whole generative process is simple, easily processes, can not increase the data burden for the treatment of facility, be easy to user's autonomous operation.
Accompanying drawing explanation
Object of the present invention, advantage and disadvantage, by for illustration and explanation for the non-limitative illustration passing through preferred embodiment below.
Fig. 1 is that user selects to need face material schematic diagram to be processed.
Fig. 2 is face size adjustment coupling schematic diagram.
Fig. 3, Fig. 4 are eye position adjustment coupling schematic diagram.
Fig. 5 is nose position adjustment coupling schematic diagram.
Fig. 6 is face position adjustment coupling schematic diagram.
Fig. 7 is that 3D face image details modifies schematic diagram.
Embodiment
A kind of method automatically generating 3D face according to photo as shown in Fig. 1 ~ 7, its unusual part is to comprise the following steps: first, as shown in Figure 1, and user selects to need face material to be processed, generates 3D face image.Specifically, in order to the face realized by all kinds of means is uploaded, the picture file that face material provides for user, or for user take pictures obtain human face photo.During enforcement, picture file is cartoon figure, or is portrait photo.Like this, be convenient to user and carry out DIY setting.Meanwhile, in order to improve application,
Afterwards, adjustment coupling 3D face image.Consider the common use habit and aesthetic value that meet people, adjustment matching content comprises, face size, eye position, nose position, face position, both as shown in figures 2-6.In order to the performance of subsequent animation is accurate, eye position comprises eyebrow distribution and eyes opening and closing scope, and face position comprises face opening and closing scope.
Then, as shown in Figure 7, carry out 3D face image details to modify.Specifically, in order to meet the individual demand of user, allow 3D face image variously not repeat, the 3D face image details of employing comprises eye color, eyes size, hair hair style, hair color, head decoration.In order to improve overall details, realize multi-level device, head decoration comprises eye shadow, cap, earphone, beard, earrings.Certainly, adjoint 3D face image, details and decoration are not limited to the content of foregoing description.
Subsequently, in order to carry out effective 3D interaction display, full animation expression being imported 3D face image, forming 3D face image finished product.Full animation expression comprises smile, laughs, opens one's eyes, closes one's eyes, opens one's mouth, shuts up, crys.Like this, the form of expression of full animation expression can be promoted.
Finally, preserve 3D face image finished product, be convenient to follow-up calling.In conjunction with actual service condition of the present invention, consider different routine calls, 3D face image finished product is kept at processing locality end, or is kept at high in the clouds.
Can be found out by above-mentioned character express, after adopting the present invention, utilize a photo, help user to generate 3D face image step by step, the details of various piece after generation, can be adjusted.Thereby, it is possible to coordinate with down-stream, the face of generation has prefabricated various expressions, carries out effective 3D face image interactive.Further, whole generative process is simple, easily processes, can not increase the data burden for the treatment of facility, be easy to user's autonomous operation.
These embodiments are only the prominent examples of application technical solution of the present invention, allly take equivalent replacement or equivalent transformation and the technical scheme that formed, all drop within the scope of protection of present invention.
Claims (9)
1. automatically generate a method for 3D face according to photo, it is characterized in that comprising the following steps:
1., user selects to need face material to be processed step, generates 3D face image;
2., adjustment coupling 3D face is vivid for step;
3. step, is carried out 3D face image details and is modified;
4. full animation expression, is imported 3D face image by step, forms 3D face image finished product;
5. step, preserves 3D face image finished product.
2. a kind of method automatically generating 3D face according to photo according to claim 1, is characterized in that: the picture file that the 1. described face material of step provides for user, or to take pictures the human face photo of acquisition for user.
3. a kind of method automatically generating 3D face according to photo according to claim 2, is characterized in that: described picture file is cartoon figure, or is portrait photo.
4. a kind of method automatically generating 3D face according to photo according to claim 1, is characterized in that: the 2. described adjustment matching content of step comprises, face size, eye position, nose position, face position.
5. a kind of method automatically generating 3D face according to photo according to claim 4, is characterized in that: described eye position comprises eyebrow distribution and eyes opening and closing scope, and described face position comprises face opening and closing scope.
6. a kind of method automatically generating 3D face according to photo according to claim 1, is characterized in that: the 3D face image details that step is 3. described, comprises eye color, eyes size, hair hair style, hair color, head decoration.
7. a kind of method automatically generating 3D face according to photo according to claim 6, is characterized in that: described head decoration comprises eye shadow, cap, earphone, beard, earrings.
8. a kind of method automatically generating 3D face according to photo according to claim 1, is characterized in that: the 4. described full animation expression of step comprises smile, laughs, opens one's eyes, closes one's eyes, opens one's mouth, shuts up, crys.
9. a kind of method automatically generating 3D face according to photo according to claim 1, is characterized in that: the 5. described 3D face image finished product of step is kept at processing locality end, or is kept at high in the clouds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310607202.8A CN104680574A (en) | 2013-11-27 | 2013-11-27 | Method for automatically generating 3D face according to photo |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310607202.8A CN104680574A (en) | 2013-11-27 | 2013-11-27 | Method for automatically generating 3D face according to photo |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104680574A true CN104680574A (en) | 2015-06-03 |
Family
ID=53315565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310607202.8A Pending CN104680574A (en) | 2013-11-27 | 2013-11-27 | Method for automatically generating 3D face according to photo |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104680574A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251294A (en) * | 2016-08-11 | 2016-12-21 | 西安理工大学 | A kind of single width is faced the virtual multi-pose of facial image and is generated method |
| CN107551549A (en) * | 2017-08-09 | 2018-01-09 | 广东欧珀移动通信有限公司 | Video game image method of adjustment and its device |
| CN107730566A (en) * | 2017-10-27 | 2018-02-23 | 朱秋华 | A kind of method, apparatus, mobile terminal and storage medium for generating expression |
| CN108734758A (en) * | 2017-04-25 | 2018-11-02 | 腾讯科技（深圳）有限公司 | A kind of model of image configuration method, device and computer storage media |
| CN114327705A (en) * | 2021-12-10 | 2022-04-12 | 重庆长安汽车股份有限公司 | Vehicle-mounted assistant virtual image self-defining method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11213132A (en) * | 1998-01-27 | 1999-08-06 | Atr Ningen Joho Tsushin Kenkyusho:Kk | Method for generating three-dimensional face model having optional expression |
| CN1949268A (en) * | 2005-10-14 | 2007-04-18 | 洪准杓 | Device and method for producing figure carving |
| WO2008144843A1 (en) * | 2007-05-31 | 2008-12-04 | Depth Analysis Pty Ltd | Systems and methods for applying a 3d scan of a physical target object to a virtual environment |
| CN101324961A (en) * | 2008-07-25 | 2008-12-17 | 上海久游网络科技有限公司 | Human face portion three-dimensional picture pasting method in computer virtual world |
| CN101344971A (en) * | 2008-08-26 | 2009-01-14 | 陈玮 | Internet three-dimensional human body head portrait spectacles try-in method |
| CN101493953A (en) * | 2009-03-04 | 2009-07-29 | 中国科学院计算技术研究所 | Interactive three-dimensional cartoon human face generating method and device |
| US20100134487A1 (en) * | 2008-12-02 | 2010-06-03 | Shang-Hong Lai | 3d face model construction method |
| CN102934144A (en) * | 2010-06-09 | 2013-02-13 | 微软公司 | Real-time animation of facial expressions |
| CN103198508A (en) * | 2013-04-07 | 2013-07-10 | 河北工业大学 | Human face expression animation generation method |
-
2013
- 2013-11-27 CN CN201310607202.8A patent/CN104680574A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11213132A (en) * | 1998-01-27 | 1999-08-06 | Atr Ningen Joho Tsushin Kenkyusho:Kk | Method for generating three-dimensional face model having optional expression |
| CN1949268A (en) * | 2005-10-14 | 2007-04-18 | 洪准杓 | Device and method for producing figure carving |
| WO2008144843A1 (en) * | 2007-05-31 | 2008-12-04 | Depth Analysis Pty Ltd | Systems and methods for applying a 3d scan of a physical target object to a virtual environment |
| CN101324961A (en) * | 2008-07-25 | 2008-12-17 | 上海久游网络科技有限公司 | Human face portion three-dimensional picture pasting method in computer virtual world |
| CN101344971A (en) * | 2008-08-26 | 2009-01-14 | 陈玮 | Internet three-dimensional human body head portrait spectacles try-in method |
| US20100134487A1 (en) * | 2008-12-02 | 2010-06-03 | Shang-Hong Lai | 3d face model construction method |
| CN101493953A (en) * | 2009-03-04 | 2009-07-29 | 中国科学院计算技术研究所 | Interactive three-dimensional cartoon human face generating method and device |
| CN102934144A (en) * | 2010-06-09 | 2013-02-13 | 微软公司 | Real-time animation of facial expressions |
| CN103198508A (en) * | 2013-04-07 | 2013-07-10 | 河北工业大学 | Human face expression animation generation method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251294A (en) * | 2016-08-11 | 2016-12-21 | 西安理工大学 | A kind of single width is faced the virtual multi-pose of facial image and is generated method |
| CN106251294B (en) * | 2016-08-11 | 2019-03-26 | 西安理工大学 | A kind of single width faces the virtual multi-pose generation method of facial image |
| CN108734758A (en) * | 2017-04-25 | 2018-11-02 | 腾讯科技（深圳）有限公司 | A kind of model of image configuration method, device and computer storage media |
| CN108734758B (en) * | 2017-04-25 | 2021-02-09 | 腾讯科技（深圳）有限公司 | Image model configuration method and device and computer storage medium |
| CN107551549A (en) * | 2017-08-09 | 2018-01-09 | 广东欧珀移动通信有限公司 | Video game image method of adjustment and its device |
| CN107730566A (en) * | 2017-10-27 | 2018-02-23 | 朱秋华 | A kind of method, apparatus, mobile terminal and storage medium for generating expression |
| CN114327705A (en) * | 2021-12-10 | 2022-04-12 | 重庆长安汽车股份有限公司 | Vehicle-mounted assistant virtual image self-defining method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509846B (en) | Image processing method, image processing apparatus, computer device, storage medium, and computer program product | |
| US20200020173A1 (en) | Methods and systems for constructing an animated 3d facial model from a 2d facial image | |
| US8437514B2 (en) | Cartoon face generation | |
| CN109377557B (en) | Real-time three-dimensional face reconstruction method based on single-frame face image | |
| CN101324961B (en) | Human face portion three-dimensional picture pasting method in computer virtual world | |
| US9196089B2 (en) | Techniques for processing reconstructed three-dimensional image data | |
| CN110390632B (en) | Image processing method and device based on dressing template, storage medium and terminal | |
| CN110688948B (en) | Method and device for transforming gender of human face in video, electronic equipment and storage medium | |
| CN104680574A (en) | Method for automatically generating 3D face according to photo | |
| CN106021550B (en) | Hair style design method and system | |
| CN102567716B (en) | Face synthetic system and implementation method | |
| KR102386642B1 (en) | Image processing method and apparatus, electronic device and storage medium | |
| CN106952221B (en) | Three-dimensional Beijing opera facial makeup automatic making-up method | |
| CN106952336B (en) | Feature-preserving human three-dimensional head portrait production method | |
| CN104331564B (en) | Adorn guidance method and terminal device based on terminal device | |
| WO2013189101A1 (en) | Hair modeling and portrait editing method based on single image | |
| CN101968892A (en) | Method for automatically adjusting three-dimensional face model according to one face picture | |
| JP2004506276A (en) | Three-dimensional face modeling system and modeling method | |
| CN105913416A (en) | Method for automatically segmenting three-dimensional human face model area | |
| JP6675384B2 (en) | Makeup support system, measuring device, portable terminal device and program | |
| CN103995911A (en) | Beauty matching method and system based on intelligent information terminal | |
| CN101968891A (en) | System for automatically generating three-dimensional figure of picture for game | |
| CN105608727A (en) | Data driving inshore surge animation synthesis method and system | |
| CN110136087A (en) | The frame self-adapting regulation method and relevant device of display terminal | |
| KR101701199B1 (en) | System and method for virtual cosmetic surgery by using mesh warping |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150603 |
|
| RJ01 | Rejection of invention patent application after publication |