Non-rigid structure from motion with complementary rank-3 spaces
Authors:
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3065-3072
Abstract
Non-rigid structure from motion (NR-SFM) is a difficult, underconstrained problem in computer vision. This paper proposes a new algorithm that revises the standard matrix factorization approach in NR-SFM. We consider two alternative representations for the linear space spanned by a small number K of 3D basis shapes. As compared to the standard approach using general rank-3K matrix factors, we show that improved results are obtained by explicitly modeling K complementary spaces of rank-3. Our new method is positively compared to the state-of-the-art in NR-SFM, providing improved results on high-frequency deformations of both articulated and simpler deformable shapes. We also present an approach for NR-SFM with occlusion.Keywords
This publication has 8 references indexed in Scilit:
- Computing Smooth Time Trajectories for Camera and Deformable Shape in Structure from Motion with OcclusionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Trajectory Space: A Dual Representation for Nonrigid Structure from MotionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Modelling and recognition of the linguistic components in American Sign LanguageImage and Vision Computing, 2009
- In defense of orthonormality constraints for nonrigid structure from motion2009
- Factorization for non-rigid and articulated structure using metric projections2009
- Optimization Algorithms on Subspaces: Revisiting Missing Data Problem in Low-Rank MatrixInternational Journal of Computer Vision, 2008
- Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical PriorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Recovering non-rigid 3D shape from image streams2002