4D Human Body Correspondences from Panoramic Depth Maps

doi:10.1109/CVPR.2018.00304

	4D Human Body Correspondences from Panoramic Depth Maps
	Zhong Li 1; Minye Wu2 ; Wangyiteng Zhou2 ; Jingyi Yu 1
	2018
会议录名称	2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
ISSN	1063-6919
页码	2877-2886
发表状态	已发表
DOI	10.1109/CVPR.2018.00304
摘要	The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes. Most existing solutions produce temporally uncorrelated point clouds or meshes with unknown point/vertex correspondences. Individually compressing each frame is ineffective and still yields to ultra-large data sizes. We present an end-to-end deep learning scheme to establish dense shape correspondences and subsequently compress the data. Our approach uses sparse set of "panoramic" depth maps or PDMs, each emulating an inward-viewing concentric mosaics (CM)[45]. We then develop a learning-based technique to learn pixel-wise feature descriptors on PDMs. The results are fed into an autoencoder-based network for compression. Comprehensive experiments demonstrate our solution is robust and effective on both public and our newly captured datasets.
关键词	Three-dimensional displays Shape Training Reliability Cameras Rendering (computer graphics) Solid modeling
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Salt Lake City, UT, United states
会议日期	18-23 June 2018
URL	查看原文
收录类别	CPCI ; CPCI-S ; EI
语种	英语
资助项目	National Science Fundation[CNS-1513031]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000457843603002
出版者	IEEE
EI入藏号	20191106642589
EI主题词	Computer vision ; Three dimensional computer graphics
EI分类号	Data Processing and Image Processing:723.2 ; Computer Applications:723.5
WOS关键词	COMPRESSION
原始文献类型	Proceedings Paper
来源库	IEEE
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/29876
专题	信息科学与技术学院信息科学与技术学院_硕士生信息科学与技术学院_博士生
作者单位	1.University of Delaware, Newark, DE, USA 2.ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Zhong Li,Minye Wu,Wangyiteng Zhou,et al. 4D Human Body Correspondences from Panoramic Depth Maps[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2018:2877-2886.