Skip to Main content Skip to Navigation
Journal articles

Multi-view occlusion reasoning for probabilistic silhouette-based dynamic scene reconstruction

Li Guan 1 Jean-Sébastien Franco 2, 3, 4 Marc Pollefeys 1, 5
3 IPARLA - Visualization and manipulation of complex data on wireless mobile devices
Université Sciences et Technologies - Bordeaux 1, Inria Bordeaux - Sud-Ouest, École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), CNRS - Centre National de la Recherche Scientifique : UMR5800
4 PERCEPTION [2007-2015] - Interpretation and Modelling of Images and Videos [2007-2015]
Inria Grenoble - Rhône-Alpes, LJK [2007-2015] - Laboratoire Jean Kuntzmann [2007-2015], Grenoble INP [2007-2019] - Institut polytechnique de Grenoble - Grenoble Institute of Technology [2007-2019]
Abstract : In this paper, we present an algorithm to probabilistically estimate object shapes in a 3D dynamic scene using their silhouette information derived from multiple geometrically calibrated video camcorders. The scene is represented by a 3D volume. Every object in the scene is associated with a distinctive label to represent its existence at every voxel location. The label links together automatically-learned view-specific appearance models of the respective object, so as to avoid the photometric calibration of the cameras. Generative probabilistic sensor models can be derived by analyzing the dependencies between the sensor observations and object labels. Bayesian reasoning is then applied to achieve robust reconstruction against real-world environment challenges, such as lighting variations, changing background etc. Our main contribution is to explicitly model the visual occlusion process and show: (1) static objects (such as trees or lamp posts), as parts of the pre-learned background model, can be automatically recovered as a byproduct of the inference; (2) ambiguities due to inter-occlusion between multiple dynamic objects can be alleviated, and the final reconstruction quality is drastically improved. Several indoor and outdoor real-world datasets are evaluated to verify our framework.
Document type :
Journal articles
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download
Contributor : Jean-Sébastien Franco <>
Submitted on : Wednesday, May 6, 2015 - 2:13:08 PM
Last modification on : Thursday, July 23, 2020 - 10:02:02 AM

Links full text



Li Guan, Jean-Sébastien Franco, Marc Pollefeys. Multi-view occlusion reasoning for probabilistic silhouette-based dynamic scene reconstruction. International Journal of Computer Vision, Springer Verlag, 2010, 90 (3), pp.283-303. ⟨10.1007/s11263-010-0341-y⟩. ⟨inria-00527803⟩



Record views