Probabilistic 3D Occupancy Flow with Latent Silhouette Cues

Li Guan (1) , Jean-Sébastien Franco (2) , Edmond Boyer (3) , Marc Pollefeys (1, 4)

1 UNC - University of North Carolina [Chapel Hill]
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 PERCEPTION - Interpretation and Modelling of Images and Videos
4 ETH Zürich - Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich]

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Li Guan, Jean-Sébastien Franco, Edmond Boyer, Marc Pollefeys. Probabilistic 3D Occupancy Flow with Latent Silhouette Cues. IEEE Computer Vision and Pattern Recognition, Jun 2010, San Francisco, United States. pp.1-8. ⟨inria-00463031v2⟩