Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

doi:10.1109/3DV.2017.00063

	Robust 3D Human Motion Reconstruction Via Dynamic Template Construction
	Li, Zhong 1,2; Ji, Yu 2; Yang, Wei 1,2; Ye, Jinwei 3; Yu, Jingyi1,2,4
	2017
会议录名称	PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV)
页码	496-505
发表状态	已发表
DOI	10.1109/3DV.2017.00063
摘要	In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field-of-view, etc. Direct estimation of 3D pose, body shape or motion on these low-quality data has been traditionally challenging. In this paper, we present a graph-based non-rigid shape registration framework that can simultaneously recover 3D human body geometry and estimate pose/motion at high fidelity. Our approach first generates a global full-body template by registering all poses in the acquired motion sequence. We then construct a deformable graph by utilizing the rigid components in the global template. We directly warp the global template graph back to each motion frame in order to fill in missing geometry. Specifically, we combine local rigidity and temporal coherence constraints to maintain geometry and motion consistencies. Comprehensive experiments on various scenes show that our method is accurate and robust even in the presence of drastic motions.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Qingdao, China
收录类别	CPCI ; EI
语种	英语
资助项目	Army Research Office[W911NF14-1-0338]
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology
WOS记录号	WOS:000454981700053
出版者	IEEE
EI入藏号	20182605362818
EI主题词	Computer vision ; Geometry ; Graphic methods ; Image reconstruction ; Surface reconstruction
EI分类号	Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Mathematics:921
WOS关键词	NONRIGID REGISTRATION ; TRACKING ; OBJECTS
原始文献类型	Proceedings Paper
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29870
专题	信息科学与技术学院信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Li, Zhong
作者单位	1.Univ Delaware, Newark, DE 19716 USA 2.Plex VR, New York, NY 10016 USA 3.Louisiana State Univ, Baton Rouge, LA 70803 USA 4.ShanghaiTech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Li, Zhong,Ji, Yu,Yang, Wei,et al. Robust 3D Human Motion Reconstruction Via Dynamic Template Construction[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:496-505.