GUAN, Li; FRANCO, Jean-Sébastien; BOYER, Edmond; POLLEFEYS, Marc

doi:10.1109/CVPR.2010.5539807

Métadonnées

Licence d’utilisation du document

GUAN, Li
University of North Carolina [Chapel Hill] [UNC]

FRANCO, Jean-Sébastien
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Visualization and manipulation of complex data on wireless mobile devices [IPARLA ]

BOYER, Edmond
Interpretation and Modelling of Images and Videos [PERCEPTION]

Langue

Communication dans un congrès

Ce document a été publié dans

CVPR 2010 - IEEE Computer Vision and Pattern Recognition, 2010-06-13, San Francisco. 2010-06-07p. 1379-1386

IEEE

Résumé en anglais

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.< Réduire

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Probabilistic 3D Occupancy Flow with Latent Silhouette Cues

Langue

Ce document a été publié dans

Résumé en anglais

URI

DOI

Origine

Unités de recherche