Learning Spatially-Smooth Mappings in Non-Rigid Structure From Motion
- 1 January 2012
- book chapter
- Published by Springer Nature
- Vol. 7575, 260-273
Abstract
Non-rigid structure from motion (NRSFM) is a classical underconstrained problem in computer vision. A common approach to make NRSFM more tractable is to constrain 3D shape deformation to be smooth over time. This constraint has been used to compress the deformation model and reduce the number of unknowns that are estimated. However, temporal smoothness cannot be enforced when the data lacks temporal ordering and its benefits are less evident when objects undergo abrupt deformations. This paper proposes a new NRSFM method that addresses these problems by considering deformations as spatial variations in shape space and then enforcing spatial, rather than temporal, smoothness. This is done by modeling each 3D shape coefficient as a function of its input 2D shape. This mapping is learned in the feature space of a rotation invariant kernel, where spatial smoothness is intrinsically defined by the mapping function. As a result, our model represents shape variations compactly using custom-built coefficient bases learned from the input data, rather than a pre-specified set such as the Discrete Cosine Transform. The resulting kernel-based mapping is a by-product of the NRSFM solution and leads to another fundamental advantage of our approach: for a newly observed 2D shape, its 3D shape is recovered by simply evaluating the learned function.Keywords
This publication has 19 references indexed in Scilit:
- Kernel non-rigid structure from motion2011
- Non-rigid structure from motion with complementary rank-3 spaces2011
- 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
- In defense of orthonormality constraints for nonrigid structure from motion2009
- Linear embeddings in non-rigid structure from motion2009
- Factorization for non-rigid and articulated structure using metric projections2009
- Rotation Invariant Kernels and Their Application to Shape AnalysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- A Factorization-Based Approach for Articulated Nonrigid Shape, Motion and Kinematic Chain Recovery From VideoIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical PriorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008