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
Generating diverse clothed 3D human animations via a generative model

文献类型：期刊论文

作者Shi, Min2; Feng, Wenke2; Gao, Lin1; Zhu, Dengming1
刊名COMPUTATIONAL VISUAL MEDIA
出版日期2024-04-01
卷号10期号:2页码:261-277
关键词Transformer garment animation conditional variational autoencoder (CVAE) computer graphics
ISSN号2096-0433
DOI10.1007/s41095-022-0324-2
英文摘要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.
资助项目National Natural Science Foundation of China[61972379]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001135210800004
出版者TSINGHUA UNIV PRESS
源URL[http://119.78.100.204/handle/2XEOYT63/38421]  
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.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, 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.

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。