Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization

doi:10.1109/TCYB.2018.2849146

	Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization
	Dong, Qiulei1,2,3 ; Wang, Hong 4
刊名	IEEE TRANSACTIONS ON CYBERNETICS
	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
DOI	10.1109/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.
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关键词	PROCRUSTEAN NORMAL-DISTRIBUTION ; 3D SHAPE ; RECONSTRUCTION ; ALGORITHMS ; ROBUST ; NMF
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000470988800028
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27845]
专题	中国科学院自动化研究所
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.