Non-rigid structure from locally-rigid motion
Authors:
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2761-2768
Abstract
We introduce locally-rigid motion, a general framework for solving the M-point, N-view structure-from-motion problem for unknown bodies deforming under orthography. The key idea is to first solve many local 3-point, N-view rigid problems independently, providing a “soup” of specific, plausibly rigid, 3D triangles. The main advantage here is that the extraction of 3D triangles requires only very weak assumptions: (1) deformations can be locally approximated by near-rigid motion of three points (i.e., stretching not dominant) and (2) local motions involve some generic rotation in depth. Triangles from this soup are then grouped into bodies, and their depth flips and instantaneous relative depths are determined. Results on several sequences, both our own and from related work, suggest these conditions apply in diverse settings - including very challenging ones (e.g., multiple deforming bodies). Our starting point is a novel linear solution to 3-point structure from motion, a problem for which no general algorithms currently exist.Keywords
This publication has 31 references indexed in Scilit:
- Capturing 3D stretchable surfaces from single images in closed form2009
- Coarse-to-fine low-rank structure-from-motion2008
- Local deformation models for monocular 3D shape recovery2008
- Surface Deformation Models for Nonrigid 3D Shape RecoveryIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Optimizing Binary MRFs via Extended Roof Duality2007
- Convex Optimization for Deformable Surface 3-D Tracking2007
- What energy functions can be minimized via graph cuts?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Robust online appearance models for visual trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Reconstruction of articulated objects from point correspondences in a single uncalibrated image2002
- Affine structure from motionJournal of the Optical Society of America A, 1991