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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 机器人视觉团队
Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization

文献类型：期刊论文

作者Dong, Qiulei1,2,3; Wang, Hong4
刊名IEEE TRANSACTIONS ON CYBERNETICS
出版日期2019-09-01
卷号49期号:9页码:3557-3570
关键词Multilinear factorization (MLF) nonrigid structure from motion (NRSFM) smoothness
ISSN号2168-2267
DOI10.1109/TCYB.2018.2849146
通讯作者Dong, Qiulei(qldong@nlpr.ia.ac.cn)
英文摘要How to implement an effective factorization for nonrigid structure from motion (NRSFM) has attracted much attention in recent years. A straightforward factorization scheme is to multilinearly solve NRSFM in an alternating manner, where each of the unknown variables in NRSFM is updated by fixing the others at each iteration. However, recent works show that most existing multilinear factorization (MLF) methods achieve poorer performances than some state-of-the-art sequential factorization methods. In this paper, we reinvestigate the MLF scheme for improving factorization accuracy, and first propose an MLF method with the only low-rank prior for NRSFM in the presence of missing data. Then, for further improving the performances of such MLF methods, a latent "smoothness" characteristic on unknown 3-D deformable shapes is investigated, which is independent of temporal relations among deformable shapes. Accordingly, a latent-smoothness prior for solving NRSFM is derived from the latent smoothness characteristic, and it is able to effectively recover 3-D deformable shapes from unordered data, which is hard for the traditional temporal-smoothness prior to handle. Finally, a regularized factorization method is proposed by integrating MLF with the explored latent-smoothness prior for further pursuing better performances. Extensive experimental results show the effectiveness of our methods in comparison to eight existing multilinear/sequential methods.
WOS关键词PROCRUSTEAN NORMAL-DISTRIBUTION ; 3D SHAPE ; RECONSTRUCTION ; ALGORITHMS ; ROBUST ; NMF
资助项目National Natural Science Foundation of China[61573359] ; National Natural Science Foundation of China[61672489] ; National Natural Science Foundation of China[61333015] ; National Natural Science Foundation of China[61375042]
WOS研究方向Automation & Control Systems ; Computer Science
语种英语
WOS记录号WOS:000470988800028
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/27845]  
专题自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者Dong, Qiulei
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Coll Life Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Dong, Qiulei,Wang, Hong. Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization[J]. IEEE TRANSACTIONS ON CYBERNETICS,2019,49(9):3557-3570.
APA Dong, Qiulei,&Wang, Hong.(2019).Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization.IEEE TRANSACTIONS ON CYBERNETICS,49(9),3557-3570.
MLA Dong, Qiulei,et al."Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization".IEEE TRANSACTIONS ON CYBERNETICS 49.9(2019):3557-3570.

入库方式： OAI收割

来源：自动化研究所

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。