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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Plausible 3D Face Wrinkle Generation Using Variational Autoencoders

文献类型：期刊论文

作者Deng, Qixin1; Ma, Luming1; Jin, Aobo1; Bi, Huikun2; Le, Binh Huy3; Deng, Zhigang1
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2022-09-01
卷号28期号:9页码:3113-3125
关键词Faces Three-dimensional displays Solid modeling Shape Computational modeling Pipelines Data models Face modeling wrinkle synthesis deep generative models variational autoencoders
ISSN号1077-2626
DOI10.1109/TVCG.2021.3051251
英文摘要Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this article we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions.
资助项目US NSF[IIS-1524782] ; US NSF[IIS-2005430] ; National Natural Science Foundation of China[62002345]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000833767700004
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/19474]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Deng, Zhigang
作者单位1.Univ Houston, Dept Comp Sci, Houston, TX 77204 USA
2.Chinese Acad Sci, Inst Comp Technol, Beijing 100864, Peoples R China
3.Elect Arts Inc, SEED Lab, Search Extraordinary Experience Div, Ashburn, VA 20147 USA
推荐引用方式
GB/T 7714		 Deng, Qixin,Ma, Luming,Jin, Aobo,et al. Plausible 3D Face Wrinkle Generation Using Variational Autoencoders[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2022,28(9):3113-3125.
APA Deng, Qixin,Ma, Luming,Jin, Aobo,Bi, Huikun,Le, Binh Huy,&Deng, Zhigang.(2022).Plausible 3D Face Wrinkle Generation Using Variational Autoencoders.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,28(9),3113-3125.
MLA Deng, Qixin,et al."Plausible 3D Face Wrinkle Generation Using Variational Autoencoders".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 28.9(2022):3113-3125.

入库方式： OAI收割

来源：计算技术研究所

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。