Generating diverse clothed 3D human animations via a generative model

doi:10.1007/s41095-022-0324-2

	Generating diverse clothed 3D human animations via a generative model
	Shi, Min 1; Feng, Wenke 1; Gao, Lin 2; Zhu, Dengming 2
	2024-04-01
发表期刊	COMPUTATIONAL VISUAL MEDIA
ISSN	2096-0433
卷号	10 期号:2 页码:261-277
摘要	Data-driven garment animation is a current topic of interest in the computer graphics industry. Existing approaches generally establish the mapping between a single human pose or a temporal pose sequence, and garment deformation, but it is difficult to quickly generate diverse clothed human animations. We address this problem with a method to automatically synthesize dressed human animations with temporal consistency from a specified human motion label. At the heart of our method is a two-stage strategy. Specifically, we first learn a latent space encoding the sequence-level distribution of human motions utilizing a transformer-based conditional variational autoencoder (Transformer-CVAE). Then a garment simulator synthesizes dynamic garment shapes using a transformer encoder-decoder architecture. Since the learned latent space comes from varied human motions, our method can generate a variety of styles of motions given a specific motion label. By means of a novel beginning of sequence (BOS) learning strategy and a self-supervised refinement procedure, our garment simulator is capable of efficiently synthesizing garment deformation sequences corresponding to the generated human motions while maintaining temporal and spatial consistency. We verify our ideas experimentally. This is the first generative model that directly dresses human animation.
关键词	Transformer garment animation conditional variational autoencoder (CVAE) computer graphics
DOI	10.1007/s41095-022-0324-2
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61972379]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001135210800004
出版者	TSINGHUA UNIV PRESS
引用统计	被引频次：1[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/2XEOYT63/38422
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhu, Dengming
作者单位	1.North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Shi, Min,Feng, Wenke,Gao, Lin,et al. Generating diverse clothed 3D human animations via a generative model[J]. COMPUTATIONAL VISUAL MEDIA,2024,10(2):261-277.
APA	Shi, Min,Feng, Wenke,Gao, Lin,&Zhu, Dengming.(2024).Generating diverse clothed 3D human animations via a generative model.COMPUTATIONAL VISUAL MEDIA,10(2),261-277.
MLA	Shi, Min,et al."Generating diverse clothed 3D human animations via a generative model".COMPUTATIONAL VISUAL MEDIA 10.2(2024):261-277.