Probabilistic 3D Occupancy Flow with Latent Silhouette Cues - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Probabilistic 3D Occupancy Flow with Latent Silhouette Cues

Abstract

In this paper we investigate shape and motion retrieval in the context of multi-camera systems. We propose a new low-level analysis based on latent silhouette cues, particularly suited for low-texture and outdoor datasets. Our analysis does not rely on explicit surface representations, instead using an EM framework to simultaneously update a set of volumetric voxel occupancy probabilities and retrieve a best estimate of the dense 3D motion field from the last consecutively observed multi-view frame set. As the framework uses only latent, probabilistic silhouette information, the method yields a promising 3D scene analysis method robust to many sources of noise and arbitrary scene objects. It can be used as input for higher level shape modeling and structural inference tasks. We validate the approach and demonstrate its practical use for shape and motion analysis experimentally.
Fichier principal
Vignette du fichier
1520.pdf (2.12 Mo) Télécharger le fichier
Vignette du fichier
occupancy-flow-teaser.png (73.13 Ko) Télécharger le fichier
CVPR2010.mp4 (9.93 Mo) Télécharger le fichier
front.PNG (223.19 Ko) Télécharger le fichier
Vignette du fichier
inria-00463031.png (223.19 Ko) Télécharger le fichier
Vignette du fichier
occupancy-flow-teaser.jpg (18.29 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Other
Format : Other
Format : Figure, Image
Format : Figure, Image
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00463031 , version 1 (10-03-2010)
inria-00463031 , version 2 (05-05-2010)
inria-00463031 , version 3 (26-07-2016)

Identifiers

Cite

Li Guan, Jean-Sébastien Franco, Edmond Boyer, Marc Pollefeys. Probabilistic 3D Occupancy Flow with Latent Silhouette Cues. CVPR 2010 - IEEE Computer Vision and Pattern Recognition, Jun 2010, San Francisco, United States. pp.1379-1386, ⟨10.1109/CVPR.2010.5539807⟩. ⟨inria-00463031v3⟩
1339 View
747 Download

Altmetric

Share

Gmail Facebook X LinkedIn More