Sequential Factorization for Nonrigid Structure from Motion via LBFGS

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 机器人视觉团队

	Sequential Factorization for Nonrigid Structure from Motion via LBFGS
	Dong, Qiulei1,3 ; Hu, Hao 2
	2016
会议日期	December 4-8, 2016
会议地点	Cancún, México
关键词	Nonrigid Structure From Motion
英文摘要	How to implement an effective factorization for nonrigid structure from motion(NRSFM) has attracted much attention in recent years. Addressing this problem, we propose a novel sequential factorization method without extra priors other than the basis low-rank prior, consisting of a motion estimation module and a 3D shape recovery module. In the motion estimation module, for improving the estimation accuracy, a novel objective function is designed for jointly pursuing the Euclidean corrective matrix and the shape coefficient matrix. And an iterative minimization algorithm is explored to solve the designed objective function based on the Limited-memory Broyden-Fletcher-Goldfarb-Shanno approach(LBFGS), naturally leading to the rotation matrix. In the 3D shape recovery module, a simple iterative algorithm is introduced for effectively computing the 3D deformable shapes with the estimated rotation matrix. The proposed extra-prior-free method is easy to implement and it can achieve an effective tradeoff between estimation accuracy and computational speed, since only several classic techniques are involved. Extensive experimental results demonstrate the effectiveness of the proposed method in comparison to five state-of-the-art methods.
会议录	Proceedings of International Conference on Pattern Recognition
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/12444]
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.Institute of Automation, Chinese Academy of Sciences 2.Shan Dong University 3.University of Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Dong, Qiulei,Hu, Hao. Sequential Factorization for Nonrigid Structure from Motion via LBFGS[C]. 见:. Cancún, México. December 4-8, 2016.