An Occupancy-Depth Generative Model of Multi-view Images

Pau Gargallo 1 Peter Sturm 1 Sergi Pujades 2
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 PRIMA - Perception, recognition and integration for observation of activity
Inria Grenoble - Rhône-Alpes, UJF - Université Joseph Fourier - Grenoble 1, INPG - Institut National Polytechnique de Grenoble , CNRS - Centre National de la Recherche Scientifique : UMR5217
Abstract : This paper presents an occupancy based generative model of stereo and multi-view stereo images. In this model, the space is divided into empty and occupied regions. The depth of a pixel is naturally determined from the occupancy as the depth of the first occupied point in its viewing ray. The color of a pixel corresponds to the color of this 3D point. This model has two theoretical advantages. First, unlike other occupancy based models, it explicitly models the deterministic relationship between occupancy and depth and, thus, it correctly handles occlusions. Second, unlike depth based approaches, determining depth from the occupancy automatically ensures the coherence of the resulting depth maps. Experimental results computing the MAP of the model using message passing techniques are presented to show the applicability of the model.
Type de document :
Communication dans un congrès
Yasushi Yagi and Sing Bing Kang and In So Kweon and Hongbin Zha. ACCV 2007 - 8th Asian Conference on Computer Vision, Nov 2007, Tokyo, Japan. Springer, 4844, pp.373-383, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-76390-1_37〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00384276
Contributeur : Peter Sturm <>
Soumis le : jeudi 14 mai 2009 - 16:54:20
Dernière modification le : jeudi 11 janvier 2018 - 06:22:03
Document(s) archivé(s) le : jeudi 10 juin 2010 - 20:00:05

Fichier

GargalloSturmPujades-accv2007....
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Pau Gargallo, Peter Sturm, Sergi Pujades. An Occupancy-Depth Generative Model of Multi-view Images. Yasushi Yagi and Sing Bing Kang and In So Kweon and Hongbin Zha. ACCV 2007 - 8th Asian Conference on Computer Vision, Nov 2007, Tokyo, Japan. Springer, 4844, pp.373-383, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-76390-1_37〉. 〈inria-00384276〉

Partager

Métriques

Consultations de la notice

220

Téléchargements de fichiers

185