DocumentCode :
1305482
Title :
Linear Local Models for Monocular Reconstruction of Deformable Surfaces
Author :
Salzmann, Mathieu ; Fua, Pascal
Author_Institution :
Toyota Technol. Inst. at Chicago, Chicago, IL, USA
Volume :
33
Issue :
5
fYear :
2011
fDate :
5/1/2011 12:00:00 AM
Firstpage :
931
Lastpage :
944
Abstract :
Recovering the 3D shape of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. Resolving the ambiguities typically requires prior knowledge about the most likely deformations that the surface may undergo. It often takes the form of a global deformation model that can be learned from training data. While effective, this approach suffers from the fact that a new model must be learned for each new surface, which means acquiring new training data, and may be impractical. In this paper, we replace the global models by linear local models for surface patches, which can be assembled to represent arbitrary surface shapes as long as they are made of the same material. Not only do they eliminate the need to retrain the model for different surface shapes, they also let us formulate 3D shape reconstruction from correspondences as either an algebraic problem that can be solved in closed form or a convex optimization problem whose solution can be found using standard numerical packages. We present quantitative results on synthetic data, as well as qualitative results on real images.
Keywords :
algebra; image reconstruction; optimisation; shape recognition; 3D shape reconstruction; algebraic problem; convex optimization problem; deformable surfaces; linear local models; monocular reconstruction; Deformable models; Image reconstruction; Shape; Surface reconstruction; Surface treatment; Three dimensional displays; Training data; Deformable surfaces; deformation models.; monocular shape recovery;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2010.158
Filename :
5557881
Link To Document :
بازگشت