[go: up one dir, main page]

CN109409274A - A kind of facial image transform method being aligned based on face three-dimensional reconstruction and face - Google Patents

A kind of facial image transform method being aligned based on face three-dimensional reconstruction and face Download PDF

Info

Publication number
CN109409274A
CN109409274A CN201811214776.8A CN201811214776A CN109409274A CN 109409274 A CN109409274 A CN 109409274A CN 201811214776 A CN201811214776 A CN 201811214776A CN 109409274 A CN109409274 A CN 109409274A
Authority
CN
China
Prior art keywords
face
dimensional
reference picture
picture
processing module
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
Application number
CN201811214776.8A
Other languages
Chinese (zh)
Other versions
CN109409274B (en
Inventor
周曦
姚鹏飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yuncong Technology Group Co Ltd
Original Assignee
Guangzhou Yuncong Artificial Intelligence Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Yuncong Artificial Intelligence Technology Co Ltd filed Critical Guangzhou Yuncong Artificial Intelligence Technology Co Ltd
Priority to CN201811214776.8A priority Critical patent/CN109409274B/en
Publication of CN109409274A publication Critical patent/CN109409274A/en
Application granted granted Critical
Publication of CN109409274B publication Critical patent/CN109409274B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Processing Or Creating Images (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Image Generation (AREA)

Abstract

一种基于人脸三维重建和人脸对齐的人脸图像变换方法，采用以下步骤，步骤1：三维图像采集装置采集人脸三维图像作为输入图像，将该输入图像传送到处理模块中；步骤2：人脸识别模块提取所述输入图像的三维特征；所述输入图像的三维特征包括人脸特征点集的坐标值；在标准人脸数据库中保存有标准人脸对齐特征集，该人脸对齐特征集由人脸对齐特征点组成，每个人脸对齐特征点为人脸上对应点的语义信息；步骤3：设置有参考图片数据库，处理模块从参考图片数据库中提取一张参考图片，传送到人脸识别模块中。基于人脸三维重建和人脸对齐的人脸图像变换方法，能够适应各种姿态和表情，对传统方法不能处理的大姿态和表情变化有效贴图。该方法还能使用一个通用模型处理所有的人脸，克服GAN方法的缺点。

A face image transformation method based on face three-dimensional reconstruction and face alignment, adopts the following steps, step 1: a three-dimensional image acquisition device collects a three-dimensional face image as an input image, and transmits the input image to a processing module; step 2 : the face recognition module extracts the three-dimensional feature of the input image; the three-dimensional feature of the input image includes the coordinate value of the face feature point set; the standard face alignment feature set is stored in the standard face database, and the face alignment feature set is stored in the standard face database. The feature set is composed of face alignment feature points, and each face alignment feature point is the semantic information of the corresponding point on the face; Step 3: A reference picture database is set up, and the processing module extracts a reference picture from the reference picture database and transmits it to the person face recognition module. The face image transformation method based on face 3D reconstruction and face alignment can adapt to various poses and expressions, and can effectively map large pose and expression changes that cannot be handled by traditional methods. The method also uses a common model to process all faces, overcoming the shortcomings of the GAN method.

Description

A kind of facial image transform method being aligned based on face three-dimensional reconstruction and face
Technical field
The present invention relates to field of image processings, and in particular to a kind of face figure being aligned based on face three-dimensional reconstruction and face As transform method.
Background technique
As the rise of artificial intelligence trend, especially depth learning technology in the broad scale research of image domains and are answered With face three-dimensional structure is rebuild and face alignment achieves the effect become better and better, the pr_net precision and speed such as proposed in the recent period Degree has reached practical requirement.
In amusement and field of play, have and much transform to a face on another image, or to facial image into The demand of edlin, such as the synthesis ancient customs or the Republic of China's photo of wechat circle of friends prevalence, synthesis admission notice etc.；It is shone in art In post-processing, need to be finely adjusted the expression of face；In game or cartoon making, need to fit to face model or The face corresponding position of person performer.
Traditional face fitting is based on key point, does triangulation according to key point, then become to each triangle It exchanges cards containing all personal details and become sworn brothers figure.This mode can only handle positive face, have the case where larger attitude angle not applicable face.
With the rise of depth learning technology, there are some face textures technologies based on GAN.As popular Deepfake. the technology based on GAN can carry out textures to the face of various postures and expression, can reach not under special scenes Wrong effect.But the mode of the not instead of textures based on GAN study, the feature of the specific face of study.This requires be directed to Each specific face trains corresponding model, and cannot use general model, this is difficult to realize under many scenes.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of facial images being aligned based on face three-dimensional reconstruction and face Transform method, specific technical solution are as follows:
A kind of facial image transform method being aligned based on face three-dimensional reconstruction and face, it is characterised in that:
Using following steps,
Step 1: three-dimensional image acquisition apparatus acquires face 3-D image as input picture, which is transmitted to In processing module；
Step 2: face recognition module extracts the three-dimensional feature of the input picture；
The three-dimensional feature of the input picture includes the coordinate value of face characteristic point set；
Standard faces alignment feature collection is preserved in standard faces database, which is aligned by face Feature point group is the semantic information of people's corresponding points on the face at, each face alignment feature point；
Step 3: being provided with reference picture database, processing module extracts one with reference to figure from reference picture database Piece is transmitted in face recognition module；
Face recognition module extracts the three-dimensional feature and face alignment feature collection of the reference picture, by the three of the reference picture Dimensional feature and face alignment feature collection are stored in volatile data base；
Step 4: processing module carries out textures to the input picture, and the texture of the input picture is fitted to reference to figure The corresponding position of piece；
Specifically, the three-dimensional feature that processing module extracts input picture obtains the texture of corresponding position；
According to the face alignment feature collection of input picture, the corresponding three-dimensional coordinate point set of reference picture is got；
Step 5: processing module will input the texture got in picture, by way of interpolation, assignment to reference picture Three-dimensional coordinate point concentrate corresponding coordinate.
Step 6: face picture is passed through graph cut into reference picture by processing module, replaces the people in reference picture Face.
Further: the step 6 is that face picture is fused to reference picture by alpha channel by processing module In.
The invention has the benefit that based on the facial image transform method that face three-dimensional reconstruction and face are aligned, it can Various postures and expression are adapted to, the big posture and the effective textures of expression shape change that cannot handle conventional method.This method can also make The shortcomings that being handled all people's face with a universal model, overcome GAN method.In addition, this method can also guarantee precision Achieve the effect that real time execution simultaneously, can effectively be applied in actual scene.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention.
Specific embodiment
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, so that advantages and features of the invention energy It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
A kind of facial image transform method being aligned based on face three-dimensional reconstruction and face as shown in Figure 1:,
Using following steps,
Step 1: three-dimensional image acquisition apparatus acquires face 3-D image as input picture, which is transmitted to In processing module；
Step 2: face recognition module extracts the three-dimensional feature of the input picture；
The three-dimensional feature of the input picture includes the coordinate value of face characteristic point set；
Standard faces alignment feature collection is preserved in standard faces database, which is aligned by face Feature point group is the semantic information of people's corresponding points on the face at, each face alignment feature point；
Step 3: being provided with reference picture database, processing module extracts one with reference to figure from reference picture database Piece is transmitted in face recognition module；
Face recognition module extracts the three-dimensional feature and face alignment feature collection of the reference picture, by the three of the reference picture Dimensional feature and face alignment feature collection are stored in volatile data base；
Step 4: processing module carries out textures to the input picture, and the texture of the input picture is fitted to reference to figure The corresponding position of piece；
Specifically, the three-dimensional feature that processing module extracts input picture obtains the texture of corresponding position；
According to the face alignment feature collection of input picture, the corresponding three-dimensional coordinate point set of reference picture is got；
Step 5: processing module will input the texture got in picture, by way of interpolation, assignment to reference picture Three-dimensional coordinate point concentrate corresponding coordinate.
Step 6: face picture is passed through alpha channel or graph cut into reference picture by processing module, is replaced Face in reference picture.

Claims (2)

1. a kind of facial image transform method being aligned based on face three-dimensional reconstruction and face, it is characterised in that:
Using following steps,
Step 1: three-dimensional image acquisition apparatus acquires face 3-D image as input picture, which is transmitted to processing In module；
Step 2: face recognition module extracts the three-dimensional feature of the input picture；
The three-dimensional feature of the input picture includes the coordinate value of face characteristic point set；
Standard faces alignment feature collection is preserved in standard faces database, the face alignment feature collection is by face alignment feature Point composition, each face alignment feature point are the semantic information of people's corresponding points on the face；
Step 3: being provided with reference picture database, processing module extracts a reference picture from reference picture database, passes It is sent in face recognition module；
Face recognition module extracts the three-dimensional feature and face alignment feature collection of the reference picture, and the three-dimensional of the reference picture is special Face alignment feature collection of seeking peace is stored in volatile data base；
Step 4: processing module carries out textures to the input picture, and the texture of the input picture is fitted to reference picture Corresponding position；
Specifically, the three-dimensional feature that processing module extracts input picture obtains the texture of corresponding position；
According to the face alignment feature collection of input picture, the corresponding three-dimensional coordinate point set of reference picture is got；
Step 5: processing module will input the texture got in picture, by way of interpolation, the three of assignment to reference picture It ties up coordinate points and concentrates corresponding coordinate.
Step 6: face picture is passed through graph cut into reference picture by processing module, replaces the face in reference picture.
2. a kind of facial image transform method being aligned based on face three-dimensional reconstruction and face according to claim 1, special Sign is: the step 6 is that face picture is fused in reference picture by processing module by alpha channel.
CN201811214776.8A 2018-10-18 2018-10-18 A face image transformation method based on face 3D reconstruction and face alignment Active CN109409274B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811214776.8A CN109409274B (en) 2018-10-18 2018-10-18 A face image transformation method based on face 3D reconstruction and face alignment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811214776.8A CN109409274B (en) 2018-10-18 2018-10-18 A face image transformation method based on face 3D reconstruction and face alignment

Publications (2)

Publication Number Publication Date
CN109409274A true CN109409274A (en) 2019-03-01
CN109409274B CN109409274B (en) 2020-09-04

Family

ID=65468396

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811214776.8A Active CN109409274B (en) 2018-10-18 2018-10-18 A face image transformation method based on face 3D reconstruction and face alignment

Country Status (1)

Country Link
CN (1) CN109409274B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111091151A (en) * 2019-12-17 2020-05-01 大连理工大学 Method for generating countermeasure network for target detection data enhancement
CN111275057A (en) * 2020-02-13 2020-06-12 腾讯科技（深圳）有限公司 Image processing method, device and equipment
CN111738087A (en) * 2020-05-25 2020-10-02 完美世界(北京)软件科技发展有限公司 Method and device for generating face model of game role
CN112330529A (en) * 2020-11-03 2021-02-05 上海镱可思多媒体科技有限公司 Dlid-based face aging method, system and terminal
CN112734890A (en) * 2020-12-22 2021-04-30 上海影谱科技有限公司 Human face replacement method and device based on three-dimensional reconstruction
CN112954205A (en) * 2021-02-04 2021-06-11 重庆第二师范学院 Image acquisition device applied to pedestrian re-identification system

Citations (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6002782A (en) * 1997-11-12 1999-12-14 Unisys Corporation System and method for recognizing a 3-D object by generating a 2-D image of the object from a transformed 3-D model
US6081275A (en) * 1997-01-10 2000-06-27 Sharp Kabushiki Kaisha Image compositing apparatus
US20030137515A1 (en) * 2002-01-22 2003-07-24 3Dme Inc. Apparatus and method for efficient animation of believable speaking 3D characters in real time
US20110115786A1 (en) * 2009-11-16 2011-05-19 Sony Corporation Image processing apparatus, image processing method, and program
CN102103756A (en) * 2009-12-18 2011-06-22 华为技术有限公司 Comic exaggeration method, device and system for human face digital image supporting position deflection
US20130129141A1 (en) * 2010-08-20 2013-05-23 Jue Wang Methods and Apparatus for Facial Feature Replacement
KR20130098824A (en) * 2012-02-28 2013-09-05 가톨릭대학교 산학협력단 3d facial pose and expression estimating method using aam and estimated depth information
CN104157010A (en) * 2014-08-29 2014-11-19 厦门幻世网络科技有限公司 3D human face reconstruction method and device
CN104637078A (en) * 2013-11-14 2015-05-20 腾讯科技（深圳）有限公司 Image processing method and device
US20150172637A1 (en) * 2013-12-12 2015-06-18 Electronics And Telecommunications Research Institute Apparatus and method for generating three-dimensional output data
CN104778712A (en) * 2015-04-27 2015-07-15 厦门美图之家科技有限公司 Method and system for pasting image to human face based on affine transformation
CN106067190A (en) * 2016-05-27 2016-11-02 俞怡斐 A kind of fast face threedimensional model based on single image generates and alternative approach
US20160335774A1 (en) * 2015-02-06 2016-11-17 Ming Chuan University Method for automatic video face replacement by using a 2d face image to estimate a 3d vector angle of the face image
CN106204750A (en) * 2016-07-11 2016-12-07 厦门幻世网络科技有限公司 A kind of method and device based on 3D source model editor's 3D object module
CN107067429A (en) * 2017-03-17 2017-08-18 徐迪 Video editing system and method that face three-dimensional reconstruction and face based on deep learning are replaced
CN107274493A (en) * 2017-06-28 2017-10-20 河海大学常州校区 A kind of three-dimensional examination hair style facial reconstruction method based on mobile platform
CN107316340A (en) * 2017-06-28 2017-11-03 河海大学常州校区 A kind of fast human face model building based on single photo
CN107945285A (en) * 2017-10-11 2018-04-20 浙江慧脑信息科技有限公司 A kind of threedimensional model is exchanged cards containing all personal details and become sworn brothers figure and deformation method
US20180144516A1 (en) * 2016-11-23 2018-05-24 3D Systems, Inc. Systems and methods for an integrated system for visualizing, simulating, modifying and 3d printing 3d objects
CN108257084A (en) * 2018-02-12 2018-07-06 北京中视广信科技有限公司 A kind of automatic cosmetic method of lightweight face based on mobile terminal
CN108447017A (en) * 2018-05-31 2018-08-24 Oppo广东移动通信有限公司 Face virtual face-lifting method and device
CN108492344A (en) * 2018-03-30 2018-09-04 中国科学院半导体研究所 A kind of portrait-cartoon generation method
CN108648142A (en) * 2018-05-21 2018-10-12 北京微播视界科技有限公司 Image processing method and device
CN108665555A (en) * 2018-05-15 2018-10-16 华中师范大学 A kind of autism interfering system incorporating real person's image

Patent Citations (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6081275A (en) * 1997-01-10 2000-06-27 Sharp Kabushiki Kaisha Image compositing apparatus
US6002782A (en) * 1997-11-12 1999-12-14 Unisys Corporation System and method for recognizing a 3-D object by generating a 2-D image of the object from a transformed 3-D model
US20030137515A1 (en) * 2002-01-22 2003-07-24 3Dme Inc. Apparatus and method for efficient animation of believable speaking 3D characters in real time
US20110115786A1 (en) * 2009-11-16 2011-05-19 Sony Corporation Image processing apparatus, image processing method, and program
CN102103756A (en) * 2009-12-18 2011-06-22 华为技术有限公司 Comic exaggeration method, device and system for human face digital image supporting position deflection
US20130129141A1 (en) * 2010-08-20 2013-05-23 Jue Wang Methods and Apparatus for Facial Feature Replacement
KR20130098824A (en) * 2012-02-28 2013-09-05 가톨릭대학교 산학협력단 3d facial pose and expression estimating method using aam and estimated depth information
CN104637078A (en) * 2013-11-14 2015-05-20 腾讯科技（深圳）有限公司 Image processing method and device
US20150172637A1 (en) * 2013-12-12 2015-06-18 Electronics And Telecommunications Research Institute Apparatus and method for generating three-dimensional output data
CN104157010A (en) * 2014-08-29 2014-11-19 厦门幻世网络科技有限公司 3D human face reconstruction method and device
US20160335774A1 (en) * 2015-02-06 2016-11-17 Ming Chuan University Method for automatic video face replacement by using a 2d face image to estimate a 3d vector angle of the face image
CN104778712A (en) * 2015-04-27 2015-07-15 厦门美图之家科技有限公司 Method and system for pasting image to human face based on affine transformation
CN106067190A (en) * 2016-05-27 2016-11-02 俞怡斐 A kind of fast face threedimensional model based on single image generates and alternative approach
CN106204750A (en) * 2016-07-11 2016-12-07 厦门幻世网络科技有限公司 A kind of method and device based on 3D source model editor's 3D object module
WO2018097880A1 (en) * 2016-11-23 2018-05-31 3Dsystems, Inc. Systems and methods for an integrated system for visualizing, simulating, modifying and 3d printing 3d objects
US20180144516A1 (en) * 2016-11-23 2018-05-24 3D Systems, Inc. Systems and methods for an integrated system for visualizing, simulating, modifying and 3d printing 3d objects
CN107067429A (en) * 2017-03-17 2017-08-18 徐迪 Video editing system and method that face three-dimensional reconstruction and face based on deep learning are replaced
CN107274493A (en) * 2017-06-28 2017-10-20 河海大学常州校区 A kind of three-dimensional examination hair style facial reconstruction method based on mobile platform
CN107316340A (en) * 2017-06-28 2017-11-03 河海大学常州校区 A kind of fast human face model building based on single photo
CN107945285A (en) * 2017-10-11 2018-04-20 浙江慧脑信息科技有限公司 A kind of threedimensional model is exchanged cards containing all personal details and become sworn brothers figure and deformation method
CN108257084A (en) * 2018-02-12 2018-07-06 北京中视广信科技有限公司 A kind of automatic cosmetic method of lightweight face based on mobile terminal
CN108492344A (en) * 2018-03-30 2018-09-04 中国科学院半导体研究所 A kind of portrait-cartoon generation method
CN108665555A (en) * 2018-05-15 2018-10-16 华中师范大学 A kind of autism interfering system incorporating real person's image
CN108648142A (en) * 2018-05-21 2018-10-12 北京微播视界科技有限公司 Image processing method and device
CN108447017A (en) * 2018-05-31 2018-08-24 Oppo广东移动通信有限公司 Face virtual face-lifting method and device

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
D.BITOUK等: "Face Swapping: Automatically Replacing Faces in Photographs", 《HTTPS://WWW1.CS.COLUMBIA.EDU/CAVE/PROJECTS/FACE_REPLACE/》 *
张金玉著: "《红外热波检测及其图像序列处理技术》", 31 July 2015, 国防工业出版社 *
陆炎: "自动三维人脸迁移算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111091151A (en) * 2019-12-17 2020-05-01 大连理工大学 Method for generating countermeasure network for target detection data enhancement
CN111275057A (en) * 2020-02-13 2020-06-12 腾讯科技（深圳）有限公司 Image processing method, device and equipment
CN111275057B (en) * 2020-02-13 2023-06-20 腾讯科技（深圳）有限公司 Image processing method, device and equipment
CN111738087A (en) * 2020-05-25 2020-10-02 完美世界(北京)软件科技发展有限公司 Method and device for generating face model of game role
CN111738087B (en) * 2020-05-25 2023-07-25 完美世界(北京)软件科技发展有限公司 Method and device for generating face model of game character
CN112330529A (en) * 2020-11-03 2021-02-05 上海镱可思多媒体科技有限公司 Dlid-based face aging method, system and terminal
CN112734890A (en) * 2020-12-22 2021-04-30 上海影谱科技有限公司 Human face replacement method and device based on three-dimensional reconstruction
CN112734890B (en) * 2020-12-22 2023-11-10 上海影谱科技有限公司 Face replacement method and device based on three-dimensional reconstruction
CN112954205A (en) * 2021-02-04 2021-06-11 重庆第二师范学院 Image acquisition device applied to pedestrian re-identification system

Also Published As

Publication number Publication date
CN109409274B (en) 2020-09-04

Similar Documents

Publication Publication Date Title
CN109409274A (en) A kind of facial image transform method being aligned based on face three-dimensional reconstruction and face
Zuffi et al. Lions and tigers and bears: Capturing non-rigid, 3d, articulated shape from images
CN102332095B (en) Face motion tracking method, face motion tracking system and method for enhancing reality
CN105631861B (en) Restore the method for 3 D human body posture from unmarked monocular image in conjunction with height map
CN105389539B (en) A method and system for 3D gesture pose estimation based on depth data
CN103593870B (en) A kind of image processing apparatus based on face and method thereof
WO2021093453A1 (en) Method for generating 3d expression base, voice interactive method, apparatus and medium
CN109242950A (en) Multi-angle of view human body dynamic three-dimensional reconstruction method under more close interaction scenarios of people
CN102831401A (en) Method and system for tracking, three-dimensionally superposing and interacting target object without special mark
CN104899563A (en) Two-dimensional face key feature point positioning method and system
JP2019096113A (en) Processing device, method and program relating to keypoint data
CN113807287B (en) A 3D structured light face recognition method
CN112733704B (en) Image processing method, electronic device, and computer-readable storage medium
CN103268629A (en) Real-time Restoration of 3D Human Shape and Posture without Markers
CN110660076A (en) Face exchange method
CN104157001A (en) Method and device for drawing head caricature
CN102103689A (en) Frontal face image synthesis-based face recognition method
CN107886558A (en) A kind of human face expression cartoon driving method based on RealSense
CN114612930A (en) Millimeter wave image suspicious object image doll mapping method
CN107748798A (en) A kind of hand-drawing image search method based on multilayer visual expression and depth network
CN110188667A (en) A Face Alignment Method Based on Tripartite Adversarial Generative Network
CN111881807A (en) VR conference control system and method based on face modeling and expression tracking
CN105224910B (en) A kind of system and method for the common notice of training
Kerdvibulvech et al. A new 3D augmented reality application for educational games to help children in communication interactively
Wang et al. Learning 3d face representation with vision transformer for masked face recognition

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
TA01 Transfer of patent application right

Effective date of registration: 20200814

Address after: No.99, Jingrong South 3rd Street, Jiancha street, Tianfu New District, Chengdu 610000 China (Sichuan) pilot Free Trade Zone, Chengdu

Applicant after: Sichuan Yuncong Tianfu Artificial Intelligence Technology Co.,Ltd.

Address before: 511457 X1301-G4169, No. 106 Fengze East Road, Nansha District, Guangzhou City, Guangdong Province

Applicant before: GUANGZHOU CLOUDWALK ARTIFICIAL INTELLIGENCE TECHNOLOGY Co.,Ltd.

TA01 Transfer of patent application right
TR01 Transfer of patent right

Effective date of registration: 20250715

Address after: 511457 Guangdong Province Guangzhou City Nansha District Nansha Street Jinlong Road No. 37 501 Room (Office Only)

Patentee after: Yuncong Technology Group Co.,Ltd.

Country or region after: China

Address before: No.99, Jingrong South 3rd Street, Jiancha street, Tianfu New District, Chengdu 610000 China (Sichuan) pilot Free Trade Zone, Chengdu

Patentee before: Sichuan Yuncong Tianfu Artificial Intelligence Technology Co.,Ltd.

Country or region before: China

TR01 Transfer of patent right