WO2020037678A1 - Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse - Google Patents

Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse Download PDF

Info

Publication number
WO2020037678A1
WO2020037678A1 PCT/CN2018/102331 CN2018102331W WO2020037678A1 WO 2020037678 A1 WO2020037678 A1 WO 2020037678A1 CN 2018102331 W CN2018102331 W CN 2018102331W WO 2020037678 A1 WO2020037678 A1 WO 2020037678A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature point
point information
face image
feature
image
Prior art date
Application number
PCT/CN2018/102331
Other languages
English (en)
Chinese (zh)
Inventor
李建亿
朱利明
Original Assignee
太平洋未来科技（深圳）有限公司
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 太平洋未来科技（深圳）有限公司 filed Critical 太平洋未来科技（深圳）有限公司
Priority to PCT/CN2018/102331 priority Critical patent/WO2020037678A1/fr
Priority to CN201811022562.0A priority patent/CN109285216B/zh
Publication of WO2020037678A1 publication Critical patent/WO2020037678A1/fr

Links

Images

Classifications

    • 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
    • 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
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20—Indexing scheme for editing of 3D models
    • G06T2219/2016—Rotation, translation, scaling
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • portable electronic devices are increasingly using three-dimensional face reconstruction technology for entertainment purposes.
  • Two-dimensional face images are obtained mainly through the camera of the electronic device, and the reconstruction effect of the three-dimensional face images in the later period depends in part on the acquisition by the previous camera.
  • the quality of the image, and the quality of the acquired image depends in part on the effect of the shake processing when shooting.
  • the current portable electronic devices mainly perform anti-shake processing through software, and the hardware has not been targeted for improvement.
  • the regression model is a predictive modeling technique that studies the relationship between the dependent variable (target) and the independent variable (predictor).
  • An important method for studying regression models is regression analysis.
  • Common regression analysis mathematical models include linear regression mathematical models, logistic regression mathematical models, polynomial regression mathematical models, stepwise regression mathematical models, and lasso regression mathematical models. These are commonly used in this field.
  • the regression model is not limited to the specific regression model used in this embodiment. The above regression models can be used in the present invention, and will not be repeated here.
  • a judging module 100 is configured to recognize a target face image in a picture and determine whether a rotation angle of the target face is greater than a preset threshold; a recognition module 200 is configured to pre-train when the rotation angle is greater than a preset threshold The regression model of the target facial feature recognizes feature point information in the target face image, the first feature point information includes first visible feature point information and first invisible feature point information; an input module 300 is configured to convert the first The feature point information is input to a pre-trained convolutional neural network model to obtain a three-dimensional face image corresponding to the target face image.
  • the temperature of the wire is increased, and the shape memory alloy wire is stretched to drive the crank link mechanism.
  • the crank of the crank link mechanism drives the rotation shaft 3302 to rotate the inner ring of the one-way bearing 3303.
  • the inner The ring drives the outer ring to rotate, and the rotating ring gear 3304 drives the movable plate 3100 through the strip groove 3110.
  • the following describes the working process of the mechanical image stabilizer 3000 of this embodiment in detail in combination with the above structure.
  • the movable plate 3100 needs to be compensated for forward motion, and then Left motion compensation once.
  • the gyroscope feeds the detected lens 1000 shake direction and distance in advance to the processing module.
  • the processing module calculates the required movement distance of the movable plate 3100, and then drives the first compensation component 3310.
  • the driving member 3301 causes the rotating shaft 3302 to drive the inner ring of the one-way bearing 3303.
  • the applicant found that the combination of the mobile phone mounting base 6100 and the support pole 6200 takes up a lot of space. Even if the support pole 6200 is retractable, the mobile phone mounting base 6100 cannot undergo structural changes and the volume will not be further reduced. Putting it in a pocket or a small bag causes the inconvenience of carrying the bracket 6000. Therefore, in this embodiment, a second step improvement is performed on the bracket 6000, so that the overall accommodation of the bracket 6000 is further improved.
  • a first connection portion is also provided on one side of the third plate body 6123, and a side surface where the connection plate 6110 is in contact with the third plate body 6123 is provided with the first connection portion.
  • a first mating portion that mates with a connecting portion.
  • the first connecting portion of this embodiment is a convex strip or protrusion (not shown in the figure), and the first matching portion is a card slot (not shown in the figure) opened on the connecting plate 6110.
  • each embodiment can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware.
  • the above-mentioned technical solution in essence or a part that contributes to the existing technology may be embodied in the form of a software product, and the computer software product may be stored in a computer-readable storage medium, the computer-readable record A medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer).

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Graphics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Architecture (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

L'invention concerne un procédé, un dispositif et un appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse. Le procédé consiste : à reconnaître une image de visage humain cible dans une image, et à déterminer si un angle de rotation d'un visage humain cible est supérieur à un premier seuil prédéfini (S101) ; à reconnaître, lorsque l'angle de rotation est supérieur au premier seuil prédéfini, des informations de point caractéristique dans l'image de visage humain cible au moyen d'un modèle de régression pré-appris, les premières informations de point de caractéristique comprenant des premières informations de point de caractéristique visible et des premières informations de point de caractéristique non visible (S102) ; et à entrer les premières informations de point caractéristique dans un modèle pré-appris de réseau de neurones à convolution, de façon à obtenir une image tridimensionnelle de visage humain correspondant à l'Image de visage humain cible (S103). Le problème décrit par la présente invention est d'éviter la difficulté de reconnaître un point caractéristique, et de localiser et de générer une image tridimensionnelle du visage humain provoquée par une auto-occlusion. La solution selon l'invention porte sur un procédé, un dispositif et un appareil électronique permettant d'améliorer la génération d'une image tridimensionnelle du visage humain, ce qui améliore le degré de correspondance.
PCT/CN2018/102331 2018-08-24 2018-08-24 Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse WO2020037678A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/102331 WO2020037678A1 (fr) 2018-08-24 2018-08-24 Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse
CN201811022562.0A CN109285216B (zh) 2018-08-24 2018-09-03 基于遮挡图像生成三维人脸图像方法、装置及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/102331 WO2020037678A1 (fr) 2018-08-24 2018-08-24 Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse

Publications (1)

Publication Number Publication Date
WO2020037678A1 true WO2020037678A1 (fr) 2020-02-27

Family

ID=65184352

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/102331 WO2020037678A1 (fr) 2018-08-24 2018-08-24 Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse

Country Status (2)

Country Link
CN (1) CN109285216B (fr)
WO (1) WO2020037678A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111583105A (zh) * 2020-05-14 2020-08-25 厦门美图之家科技有限公司 人像生成方法、装置、设备及存储介质
CN112037320A (zh) * 2020-09-01 2020-12-04 腾讯科技（深圳）有限公司 一种图像处理方法、装置、设备以及计算机可读存储介质
CN112580463A (zh) * 2020-12-08 2021-03-30 北京华捷艾米科技有限公司 三维人体骨架数据识别方法及装置
CN113673308A (zh) * 2021-07-05 2021-11-19 北京旷视科技有限公司 对象识别方法、装置和电子系统
WO2024088061A1 (fr) * 2022-10-27 2024-05-02 广州市百果园信息技术有限公司 Procédé, appareil et dispositif de reconnaissance de zone d'occlusion et de reconstruction de visage, et support de stockage

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886226B (zh) * 2019-02-27 2020-12-01 北京达佳互联信息技术有限公司 确定图像的特征数据的方法、装置、电子设备及存储介质
CN109902767B (zh) * 2019-04-11 2021-03-23 网易（杭州）网络有限公司 模型训练方法、图像处理方法及装置、设备和介质
CN110826395B (zh) * 2019-09-18 2023-10-31 平安科技（深圳）有限公司 人脸旋转模型的生成方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104899563A (zh) * 2015-05-29 2015-09-09 深圳大学 一种二维人脸关键特征点定位方法及系统
CN107194356A (zh) * 2017-05-25 2017-09-22 湖南警察学院 基于人工神经网络的人脸检测识别方法
CN107423678A (zh) * 2017-05-27 2017-12-01 电子科技大学 一种提取特征的卷积神经网络的训练方法及人脸识别方法
CN108133220A (zh) * 2016-11-30 2018-06-08 北京市商汤科技开发有限公司 模型训练、关键点定位及图像处理方法、系统及电子设备
CN108388889A (zh) * 2018-03-23 2018-08-10 百度在线网络技术（北京）有限公司 用于分析人脸图像的方法和装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100066678A (ko) * 2008-12-10 2010-06-18 삼성전기주식회사 손떨림 보정장치를 구비한 카메라 모듈
CN105550637B (zh) * 2015-12-04 2019-03-08 小米科技有限责任公司 轮廓点定位方法及装置
CN106157372B (zh) * 2016-07-25 2019-01-25 深圳市唯特视科技有限公司 一种基于视频图像的3d人脸网格重构方法
CN107871099A (zh) * 2016-09-23 2018-04-03 北京眼神科技有限公司 人脸定位方法和装置
CN107729838A (zh) * 2017-10-12 2018-02-23 中科视拓（北京）科技有限公司 一种基于深度学习的头部姿态估算方法
CN107680158A (zh) * 2017-11-01 2018-02-09 长沙学院 一种基于卷积神经网络模型的三维人脸重建方法
CN108399649B (zh) * 2018-03-05 2021-07-20 中科视拓（北京）科技有限公司 一种基于级联回归网络的单张图片三维人脸重建方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104899563A (zh) * 2015-05-29 2015-09-09 深圳大学 一种二维人脸关键特征点定位方法及系统
CN108133220A (zh) * 2016-11-30 2018-06-08 北京市商汤科技开发有限公司 模型训练、关键点定位及图像处理方法、系统及电子设备
CN107194356A (zh) * 2017-05-25 2017-09-22 湖南警察学院 基于人工神经网络的人脸检测识别方法
CN107423678A (zh) * 2017-05-27 2017-12-01 电子科技大学 一种提取特征的卷积神经网络的训练方法及人脸识别方法
CN108388889A (zh) * 2018-03-23 2018-08-10 百度在线网络技术（北京）有限公司 用于分析人脸图像的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LIU, GANG: "Research on 3D Face Reconstruction Algorithm Based on Self-occlusion", INFORMATION & TECHNOLOGY, CHINA MASTER-'S THESES FULL-TEXT DATABASE, 15 March 2018 (2018-03-15), ISSN: 1674-0246 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111583105A (zh) * 2020-05-14 2020-08-25 厦门美图之家科技有限公司 人像生成方法、装置、设备及存储介质
CN112037320A (zh) * 2020-09-01 2020-12-04 腾讯科技（深圳）有限公司 一种图像处理方法、装置、设备以及计算机可读存储介质
CN112037320B (zh) * 2020-09-01 2023-10-20 腾讯科技（深圳）有限公司 一种图像处理方法、装置、设备以及计算机可读存储介质
CN112580463A (zh) * 2020-12-08 2021-03-30 北京华捷艾米科技有限公司 三维人体骨架数据识别方法及装置
CN113673308A (zh) * 2021-07-05 2021-11-19 北京旷视科技有限公司 对象识别方法、装置和电子系统
WO2024088061A1 (fr) * 2022-10-27 2024-05-02 广州市百果园信息技术有限公司 Procédé, appareil et dispositif de reconnaissance de zone d'occlusion et de reconstruction de visage, et support de stockage

Also Published As

Publication number Publication date
CN109285216A (zh) 2019-01-29
CN109285216B (zh) 2023-06-09

Similar Documents

Publication Publication Date Title
WO2020037678A1 (fr) Procédé, dispositif et appareil électronique permettant de générer une image tridimensionnelle de visage humain à partir d'une image occluse
WO2020037676A1 (fr) Procédé et appareil de génération d'images tridimensionnelles de visage, et dispositif électronique
WO2020037679A1 (fr) Procédé et appareil de traitement vidéo, et dispositif électronique
WO2020037680A1 (fr) Procédé et appareil d'optimisation de visage en trois dimensions à base de lumière et dispositif électronique
CN108596827B (zh) 三维人脸模型生成方法、装置及电子设备
CN109727303B (zh) 视频展示方法、系统、计算机设备、存储介质和终端
WO2020037681A1 (fr) Procédé et appareil de génération de vidéo, et dispositif électronique
US9479736B1 (en) Rendered audiovisual communication
WO2019205284A1 (fr) Procédé et appareil d'imagerie ar
JP5784226B2 (ja) 画像モデルの構築のための方法および装置
US20220156998A1 (en) Multiple device sensor input based avatar
BR112015014629A2 (pt) método para operar um sistema que possui um monitor, uma câmera e um processador
CN108537870B (zh) 图像处理方法、装置及电子设备
WO2020056689A1 (fr) Procédé et appareil d'imagerie ra et dispositif électronique
CN108200337B (zh) 拍照处理的方法、装置、终端及存储介质
WO2020056692A1 (fr) Procédé et appareil d'interaction d'informations et dispositif électronique
US9747695B2 (en) System and method of tracking an object
CN112257696A (zh) 视线估计方法及计算设备
CN108377398A (zh) 基于红外的ar成像方法、系统及电子设备
TW202301277A (zh) 來自雙眼視訊的即時3d面部動畫
US11893681B2 (en) Method for processing two-dimensional image and device for executing method
WO2023142886A1 (fr) Procédé de transfert d'expression, procédé d'apprentissage de modèle et dispositif
CN116095353A (zh) 基于体积视频的直播方法、装置、电子设备及存储介质
WO2020056693A1 (fr) Procédé et appareil de synthétisation d'image et dispositif électronique
KR20200071008A (ko) 2차원 이미지 처리 방법 및 이 방법을 실행하는 디바이스

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18930943

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18930943

Country of ref document: EP

Kind code of ref document: A1