Propagated Photoconsistency and Convexity in Variational Multiview 3D Reconstruction

Abstract : In this paper, we make two contributions. Firstly, we replace the generic balloon constraints widely used in 3D reconstruction by a more sophisticated data-dependent regional term. The key idea is to propagate classical photoconsistency along visual rays into regional values describing voxel probabilities for being inside or outside the observed object. Secondly, we cast the optimization as one of minimizing a convex functional. Therefore (up to visibility) the reconstruction problem can be solved in a globally optimal manner in a spatially continuous setting. Compared to graph cut methods, this approach does not suffer from discretization artifacts and exhibits considerable reduction in memory requirements. Experimental comparisons clearly show the advantages of the proposed technique.
Type de document :
Communication dans un congrès
Peter Belhumeur and Katsushi Ikeuchi and Emmanuel Prados and Stefano Soatto and Peter Sturm. Proceedings of the First International Workshop on Photometric Analysis For Computer Vision - PACV 2007, Oct 2007, Rio de Janeiro, Brazil. INRIA, 8 p., 2007
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00265725
Contributeur : Inria Rhône-Alpes Documentation <>
Soumis le : jeudi 20 mars 2008 - 09:24:28
Dernière modification le : jeudi 20 mars 2008 - 09:30:50
Document(s) archivé(s) le : vendredi 28 septembre 2012 - 11:30:43

Fichier

p24.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00265725, version 1

Collections

Citation

Kalin Kolev, Maria Klodt, Thomas Brox, Daniel Cremers. Propagated Photoconsistency and Convexity in Variational Multiview 3D Reconstruction. Peter Belhumeur and Katsushi Ikeuchi and Emmanuel Prados and Stefano Soatto and Peter Sturm. Proceedings of the First International Workshop on Photometric Analysis For Computer Vision - PACV 2007, Oct 2007, Rio de Janeiro, Brazil. INRIA, 8 p., 2007. 〈inria-00265725〉

Partager

Métriques

Consultations de la notice

225

Téléchargements de fichiers

172