DocumentCode :
2716079
Title :
A simple prior-free method for non-rigid structure-from-motion factorization
Author :
Dai, Yuchao ; Li, Hongdong ; He, Mingyi
Author_Institution :
Northwestern Polytech. Univ., Xi´´an, China
fYear :
2012
fDate :
16-21 June 2012
Firstpage :
2018
Lastpage :
2025
Abstract :
This paper proposes a simple “prior-free” method for solving non-rigid structure-from-motion factorization problems. Other than using the basic low-rank condition, our method does not assume any extra prior knowledge about the nonrigid scene or about the camera motions. Yet, it runs reliably, produces optimal result, and does not suffer from the inherent basis-ambiguity issue which plagued many conventional nonrigid factorization techniques. Our method is easy to implement, which involves solving no more than an SDP (semi-definite programming) of small and fixed size, a linear Least-Squares or trace-norm minimization. Extensive experiments have demonstrated that it outperforms most of the existing linear methods of nonrigid factorization. This paper offers not only new theoretical insight, but also a practical, everyday solution, to non-rigid structure-from-motion.
Keywords :
computational geometry; computer vision; image motion analysis; least squares approximations; mathematical programming; matrix decomposition; minimisation; SDP; basis-ambiguity issue; camera motions; geometric computer vision problem; linear least-squares; low-rank condition; nonrigid structure-from-motion factorization; prior-free method; semidefinite programming; trace-norm minimization; Cameras; Equations; Linear systems; Minimization; Shape; Shape measurement; Trajectory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
ISSN :
1063-6919
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2012.6247905
Filename :
6247905
Link To Document :
بازگشت