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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00384276
Contributor : Peter Sturm <>
Submitted on : Thursday, May 14, 2009 - 4:54:20 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:40 AM
Long-term archiving on : Thursday, June 10, 2010 - 8:00:05 PM

File

GargalloSturmPujades-accv2007....
Files produced by the author(s)

Identifiers

Citation

Pau Gargallo, Peter Sturm, Sergi Pujades. An Occupancy-Depth Generative Model of Multi-view Images. ACCV 2007 - 8th Asian Conference on Computer Vision, Nov 2007, Tokyo, Japan. pp.373-383, ⟨10.1007/978-3-540-76390-1_37⟩. ⟨inria-00384276⟩

Share

Metrics

Record views

318

Files downloads

323