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
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;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2012.6247905