J
Jean-Sébastien Franco
Researcher at University of Grenoble
Publications - 54
Citations - 1938
Jean-Sébastien Franco is an academic researcher from University of Grenoble. The author has contributed to research in topics: Silhouette & Visual hull. The author has an hindex of 22, co-authored 54 publications receiving 1764 citations. Previous affiliations of Jean-Sébastien Franco include University of North Carolina at Chapel Hill & French Institute for Research in Computer Science and Automation.
Papers
More filters
Proceedings ArticleDOI
Exact Polyhedral Visual Hulls
TL;DR: This work proposes an exact method for efficiently and robustly computing the visual hull of an object from image contours that is fast and allows real-time recovery of both manifold and watertight visual hull polyhedra.
Proceedings ArticleDOI
Fusion of multiview silhouette cues using a space occupancy grid
TL;DR: This work proposes a new framework for multiview silhouette cue fusion that uses a space occupancy grid as a probabilistic 3D representation of scene contents, and introduces the occupancy grid concept, popular in the robotics, for multicamera environments.
Journal ArticleDOI
Efficient Polyhedral Modeling from Silhouettes
TL;DR: An efficient algorithm to compute the surface of the visual hull from silhouettes in the form of a polyhedral mesh that relies on a small number of geometric operations to compute a visual hull polyhedron in a single pass is provided.
Proceedings ArticleDOI
Moulding Humans: Non-Parametric 3D Human Shape Estimation From Single Images
TL;DR: In this paper, a non-parametric approach was proposed to estimate the 3D shape of a person from a single RGB image using a 2D depth map and a hidden depth map.
Book ChapterDOI
Estimation of Human Body Shape in Motion with Wide Clothing
Jinlong Yang,Jinlong Yang,Jean-Sébastien Franco,Jean-Sébastien Franco,Franck Hétroy-Wheeler,Franck Hétroy-Wheeler,Stefanie Wuhrer,Stefanie Wuhrer +7 more
TL;DR: This work proposes the first automatic method to solve 3D human body shape in motion from a sequence of unstructured oriented 3D point clouds that works in the presence of loose clothing by leveraging a recent robust pose detection method.