Plausible 3D Face Wrinkle Generation Using Variational Autoencoders

doi:10.1109/TVCG.2021.3051251

	Plausible 3D Face Wrinkle Generation Using Variational Autoencoders
	Deng, Qixin 1; Ma, Luming 1; Jin, Aobo 1; Bi, Huikun 2; Le, Binh Huy 3; Deng, Zhigang 1
	2022-09-01
发表期刊	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
ISSN	1077-2626
卷号	28 期号:9 页码:3113-3125
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.
关键词	Faces Three-dimensional displays Solid modeling Shape Computational modeling Pipelines Data models Face modeling wrinkle synthesis deep generative models variational autoencoders
DOI	10.1109/TVCG.2021.3051251
收录类别	SCI
语种	英语
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
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000833767700004
出版者	IEEE COMPUTER SOC
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19475
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.