4D Human Body Correspondences from Panoramic Depth Maps
Li, Zhong1; Wu, Minye2; Zhou, Wangyiteng2; Yu, Jingyi1,2
2018
Source Publication2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Pages2877-2886
Status已发表
DOI10.1109/CVPR.2018.00304
AbstractThe 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.
Publication Place345 E 47TH ST, NEW YORK, NY 10017 USA
Conference PlaceSalt Lake City, UT, United states
Indexed ByCPCI ; EI
Language英语
Funding ProjectNational Science Fundation[CNS-1513031]
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000457843603002
PublisherIEEE
EI Accession Number20191106642589
EI KeywordsComputer vision ; Three dimensional computer graphics
EI Classification NumberData Processing and Image Processing:723.2 ; Computer Applications:723.5
WOS KeywordCOMPRESSION
Original Document TypeProceedings Paper
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document Type会议论文
Identifierhttps://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29876
Collection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
信息科学与技术学院_硕士生
信息科学与技术学院_博士生
Corresponding AuthorLi, Zhong
Affiliation1.Univ Delaware, Newark, DE 19716 USA
2.ShanghaiTech Univ, Shanghai, Peoples R China
Recommended Citation
GB/T 7714
Li, Zhong,Wu, Minye,Zhou, Wangyiteng,et al. 4D Human Body Correspondences from Panoramic Depth Maps[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2018:2877-2886.
Files in This Item: Download All
File Name/Size DocType Version Access License
4d-human-body-corres(7787KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Li, Zhong]'s Articles
[Wu, Minye]'s Articles
[Zhou, Wangyiteng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Zhong]'s Articles
[Wu, Minye]'s Articles
[Zhou, Wangyiteng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Zhong]'s Articles
[Wu, Minye]'s Articles
[Zhou, Wangyiteng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 4d-human-body-correspondences-panoramic-depth-maps.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.