Non-rigid Shape Matching Using Geometry and Photometry

Nicolas Thorstensen 1 Renaud Keriven 1
1 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : In this paper, we tackle the problem of finding correspondences between three-dimensional reconstructions of a deformable surface at different time steps. We suppose that (i) the mechanical underlying model imposes time-constant geodesic distances between points on the surface; and that (ii) images of the real surface are available. This is for instance the case in spatio-temporal shape from videos (e.g. multi-view stereo, visual hulls, etc.) when the surface is supposed approximatively unstretchable. These assumptions allow to exploit both geometry and photometry. In particular we propose an energy based formulation of the problem, extending the work of Bronstein et of. [1]. On the one hand, we show that photometry (i) improves accuracy in case of locally elastic deformations or noisy surfaces and (ii) allows to still find the right solution when [1] fails because of ambiguities (e.g. symmetries). On the other hand, using geometry makes it possible to match shapes that have undergone large motion, which is not possible with usual photometric methods. Numerical experiments prove the efficiency of our method on synthetic and real data.
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger
Contributeur : Ist Enpc <>
Soumis le : lundi 2 juillet 2012 - 12:46:12
Dernière modification le : jeudi 31 mai 2018 - 01:04:43
Document(s) archivé(s) le : mercredi 3 octobre 2012 - 02:18:14


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00711070, version 1



Nicolas Thorstensen, Renaud Keriven. Non-rigid Shape Matching Using Geometry and Photometry. ACCV 2009 9th Asian conference on Computer Vision, Sep 2009, Xi'an, China. pp.644-654. ⟨hal-00711070⟩



Consultations de la notice


Téléchargements de fichiers