Visual Shapes of Silhouette Sets - Archive ouverte HAL Access content directly
Conference Papers Year : 2006

Visual Shapes of Silhouette Sets


Shape from silhouette methods are extensively used to model dynamic and non-rigid objects using binary foreground-background images. Since the problem of reconstructing shapes from silhouettes is ambiguous, a number of solutions exist and several approaches only consider the one with a maximal volume, called the visual hull. However, the visual hull is not always a good approximation of shapes, in particular when observing smooth surfaces with few cameras. In this paper, we consider instead a class of solutions to the silhouette reconstruction problem that we call visual shapes. Such a class includes the visual hull, but also better approximations of the observed shapes which can take into account local assumptions such as smoothness, among others. Our contributions with respect to existing works is rst to identify silhouette consistent shapes different from the visual hull, and second to give a practical way to estimate such shapes in real time. Experiments on various sets of data including human body silhouettes are shown to illustrate the principle and the interests of visual shapes.
Fichier principal
Vignette du fichier
visualshapes.pdf (1.22 Mo) Télécharger le fichier
Vignette du fichier
hal-00349020.png (83.2 Ko) Télécharger le fichier
Vignette du fichier
1-visualshapes.gif (62.7 Ko) Télécharger le fichier
Vignette du fichier
2-visualshapes.gif (9.25 Ko) Télécharger le fichier
VisualShapes.avi (6.75 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Figure, Image
Format : Figure, Image
Format : Other

Dates and versions

hal-00349020 , version 1 (22-12-2008)



Jean-Sébastien Franco, Marc Lapierre, Edmond Boyer. Visual Shapes of Silhouette Sets. Symposium on 3D Data Processing, Visualization and Transmission, Jun 2006, United States. pp.1-8, ⟨10.1109/3DPVT.2006.148⟩. ⟨hal-00349020⟩
585 View
825 Download



Gmail Facebook X LinkedIn More