Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
THREE-DIMENSIONAL HUMAN BODY MODEL RECONSTRUCTION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/156533
Kind Code:
A1
Abstract:
The present application relates to a three-dimensional human body model reconstruction method and apparatus, an electronic device, and a storage medium. The method comprises: obtaining a single-camera human body image; inputting the single-camera human body image into a human body information prediction model, and outputting target human body information in the single-camera human body image by means of the human body information prediction model; and determining a three-dimensional human body model by using figure parameters and action and posture parameters, such that human body information determined by the three-dimensional human body model matches the target human body information. The three-dimensional human body model reconstruction method and apparatus, the electronic device and the storage medium provided by embodiments of the present application can quickly and accurately reconstruct a three-dimensional human body model.

Inventors:
ZHANG JIANJIE (CN)
CHAI JINXIANG (CN)
LI MIAOPENG (CN)
XIONG XINGTANG (CN)
JIANG LIGUO (CN)
WANG CONGYI (CN)
Application Number:
PCT/CN2022/070258
Publication Date:
July 28, 2022
Filing Date:
January 05, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
MOFA SHANGHAI INFORMATION TECH CO LTD (CN)
SHANGHAI MOVU TECH CO LTD (CN)
International Classes:
G06T17/00
Foreign References:
CN112819944A2021-05-18
CN108629801A2018-10-09
CN110415336A2019-11-05
CN110298916A2019-10-01
US20180053309A12018-02-22
Other References:
ZENG ZHICHAO: "Video-based 3D Human Model Pose and Shape Reconstruction", MASTER THESIS, TIANJIN POLYTECHNIC UNIVERSITY, CN, 15 January 2019 (2019-01-15), CN , XP055953537, ISSN: 1674-0246
"Computer vision - ECCV 2016 : 14th European conference, Amsterdam, The Netherlands, October 11-14, 2016 : proceedings", vol. 9909 Chap.34, 16 September 2016, SPRINGER , Berlin, Heidelberg , ISBN: 978-3-319-46453-4, article BOGO FEDERICA; KANAZAWA ANGJOO; LASSNER CHRISTOPH; GEHLER PETER; ROMERO JAVIER; BLACK MICHAEL J.: "Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image", pages: 561 - 578, XP047355099, DOI: 10.1007/978-3-319-46454-1_34
Attorney, Agent or Firm:
LINDA LIU & PARTNERS (CN)
Download PDF: