inria-00281378, version 1
Omnidirectional texturing of human actors from multiple view video sequences
Alexandrina Orzan
a, 1Jean-Marc Hasenfratz
b, 1, 2
Romanian Conference on Computer-Human Interaction (2005) 133-136
Résumé : In 3D video, recorded object behaviors can be observed from any viewpoint, because the 3D video registers the object's 3D shape and color. However, the real-world views are limited to the views from a number of cameras, so only a coarse model of the object can be recovered in real-time. It becomes then necessary to judiciously texture the object with images recovered from the cameras. One of the problems in multi-texturing is to decide what portion of the 3D model is visible from what camera. We propose a texture-mapping algorithm that tries to bypass the problem of exactly deciding if a point is visible or not from a certain camera. Given more than two color values for each pixel, a statistical test allows to exclude outlying color data before blending.
- a – Université Pierre et Marie Curie - Paris VI
- b – Université Pierre Mendès-France - Grenoble II
- 1 : ARTIS (IMAG-INRIA Rhône-Alpes / GRAVIR)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- 2 : IUP Commerce et Vente (IUP-CV)
- Université Pierre Mendès-France - Grenoble II
- Domaine : Informatique/Synthèse d'image et réalité virtuelle
- inria-00281378, version 1
- http://hal.inria.fr/inria-00281378
- oai:hal.inria.fr:inria-00281378
- Contributeur : Jean-Marc Hasenfratz
- Soumis le : Jeudi 22 Mai 2008, 10:34:56
- Dernière modification le : Mercredi 28 Avril 2010, 16:28:34







Documents associés
Exporter