Skip to Main content Skip to Navigation
Conference papers

3D Occlusion Inference from Silhouette Cues

Abstract : We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views. While well studied and robust in controlled environments, silhouette-based reconstruction of dynamic objects fails in general environments where uncontrolled occlusions are commonplace, due to inherent silhouette corruption by occluders. We show that occluders in the interaction space of dynamic objects can be detected and their 3D shape fully recovered as a byproduct of shape-from-silhouette analysis. We provide a Bayesian sensor fusion formulation to process all occlusion cues occurring in a multi-view sequence. Results show that the shape of static occluders can be robustly recovered from pure dynamic object motion, and that this information can be used for online self-correction and consolidation of dynamic object shape reconstruction.
Document type :
Conference papers
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Jean-Sébastien Franco Connect in order to contact the contributor
Submitted on : Monday, December 22, 2008 - 6:57:27 PM
Last modification on : Wednesday, August 21, 2019 - 10:22:06 AM
Long-term archiving on: : Thursday, October 11, 2012 - 2:45:50 PM


Files produced by the author(s)


  • HAL Id : hal-00348980, version 1


Li Guan, Jean-Sébastien Franco, Marc Pollefeys. 3D Occlusion Inference from Silhouette Cues. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2007, United States. pp.1-8. ⟨hal-00348980⟩



Record views


Files downloads