Non-Rigid Shape-from-Motion for Isometric Surfaces using Infinitesimal Planarity
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.11
Abstract
This paper proposes a general framework to solve Non-Rigid Shape-from-Motion (NRSfM) with the perspective camera under isometric deformations. Contrary to the usual low-rank linear shape basis, isometry allows us to model more complex shape deformations from a sparse set of images. Existing methods suffer from ambiguities and may be very expensive to solve. We bring four main contributions. First, we formulate isometric NRSfM as a system of first-order Partial Differential Equations (PDE) involving the shape�s depth and normal field and an unknown template. Second, we show this system cannot be locally resolved. Third, we introduce the concept of infinitesimal planarity and show that it makes the system locally solvable for at least three views. Fourth, we derive an analytical solution which involves convex, linear least-squares optimization only, outperforming existing work on challenging datasets.
Session
Video and Structure From Motion
Files
Extended Abstract (PDF, 1 page, 185K)Paper (PDF, 12 pages, 1.3M)
Bibtex File
Presentation
Citation
Ajad Chhatkuli, Daniel Pizarro, and Adrien Bartoli. Non-Rigid Shape-from-Motion for Isometric Surfaces using Infinitesimal Planarity. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.11
title = {Non-Rigid Shape-from-Motion for Isometric Surfaces using Infinitesimal Planarity},
author = {Chhatkuli, Ajad and Pizarro, Daniel and Bartoli, Adrien},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.11 }
}