Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users

doi:10.1111/cgf.14634

	Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users
	Ye, Yongjing 1,2; Liu, Libin 3; Hu, Lei 1,2; Xia, Shihong 1,2
	2022-12-01
发表期刊	COMPUTER GRAPHICS FORUM
ISSN	0167-7055
卷号	41 期号:8 页码:183-194
摘要	Animating an avatar that reflects a user's action in the VR world enables natural interactions with the virtual environment. It has the potential to allow remote users to communicate and collaborate in a way as if they met in person. However, a typical VR system provides only a very sparse set of up to three positional sensors, including a head-mounted display (HMD) and Optionally two hand-held controllers, making the estimation of the user's full-body movement a difficult problem. In this work, we present a data-driven physics-based method for predicting the realistic full-body movement of the user according to the transformations of these VR trackers and simulating an avatar character to mimic such user actions in the virtual world in realtime. We train our system using reinforcement learning with carefully designed pretraining processes to ensure the success of the training and the quality of the simulation. We demonstrate the effectiveness of the method with an extensive set of examples.
DOI	10.1111/cgf.14634
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of Science and Technology for Winter Olympics[2020YFF0304701] ; National Natural Science Foundation of China[61772499]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001047605100018
出版者	WILEY
引用统计	被引频次：11[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/2XEOYT63/21174
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Libin; Xia, Shihong
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Peking Univ, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ye, Yongjing,Liu, Libin,Hu, Lei,et al. Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users[J]. COMPUTER GRAPHICS FORUM,2022,41(8):183-194.
APA	Ye, Yongjing,Liu, Libin,Hu, Lei,&Xia, Shihong.(2022).Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users.COMPUTER GRAPHICS FORUM,41(8),183-194.
MLA	Ye, Yongjing,et al."Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users".COMPUTER GRAPHICS FORUM 41.8(2022):183-194.