中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Beyond 3DMM: Learning to Capture High-Fidelity 3D Face Shape

文献类型：期刊论文

作者Zhu, Xiangyu4,5,6; Yu, Chang4,5,6; Huang, Di3; Lei, Zhen2,4,5,6; Wang, Hao4,5,6; Li, Stan Z.1
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-02-01
卷号45期号:2页码:1442-1457
关键词3D face face reconstruction 3DMM fine-grained personalized 3D face dataset
ISSN号0162-8828
DOI10.1109/TPAMI.2022.3164131
通讯作者Lei, Zhen(zlei@nlpr.ia.ac.cn)
英文摘要3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is attributed to insufficient ground-truth 3D shapes, unreliable training strategies and limited representation power of 3DMM. To alleviate this issue, this paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person. Specifically, given a 2D image as the input, we virtually render the image in several calibrated views to normalize pose variations while preserving the original image geometry. A many-to-one hourglass network serves as the encode-decoder to fuse multiview features and generate vertex displacements as the fine-grained geometry. Besides, the neural network is trained by directly optimizing the visual effect, where two 3D shapes are compared by measuring the similarity between the multiview images rendered from the shapes. Finally, we propose to generate the ground-truth 3D shapes by registering RGB-D images followed by pose and shape augmentation, providing sufficient data for network training. Experiments on several challenging protocols demonstrate the superior reconstruction accuracy of our proposal on the face shape.
WOS关键词RECONSTRUCTION
资助项目National Key Research & Development Program[2020AAA0140002] ; Chinese National Natural Science Foundation[62176256] ; Chinese National Natural Science Foundation[61876178] ; Chinese National Natural Science Foundation[61872367] ; Chinese National Natural Science Foundation[61976229] ; Chinese National Natural Science Foundation[62106264] ; Chinese National Natural Science Foundation[62176012] ; Chinese National Natural Science Foundation[62022011] ; Youth Innovation Promotion Association CAS[Y2021131] ; InnoHK program
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000912386000007
出版者IEEE COMPUTER SOC
资助机构National Key Research & Development Program ; Chinese National Natural Science Foundation ; Youth Innovation Promotion Association CAS ; InnoHK program
源URL[http://ir.ia.ac.cn/handle/173211/51338]  
专题多模态人工智能系统全国重点实验室
通讯作者Lei, Zhen
作者单位1.Westlake Univ, Sch Engn, Hangzhou 310024, Zhejiang, Peoples R China
2.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, Hong Kong Inst Sci & Innovat, Hong Kong, Peoples R China
3.Beihang Univ, Key Lab Software Dev Environm, Sch Comp Sci & Engn, Beijing 100191, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
5.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
6.Chinese Acad Sci, Ctr Biometr & Secur Res, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Zhu, Xiangyu,Yu, Chang,Huang, Di,et al. Beyond 3DMM: Learning to Capture High-Fidelity 3D Face Shape[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(2):1442-1457.
APA Zhu, Xiangyu,Yu, Chang,Huang, Di,Lei, Zhen,Wang, Hao,&Li, Stan Z..(2023).Beyond 3DMM: Learning to Capture High-Fidelity 3D Face Shape.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(2),1442-1457.
MLA Zhu, Xiangyu,et al."Beyond 3DMM: Learning to Capture High-Fidelity 3D Face Shape".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.2(2023):1442-1457.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。