Image-Based Rendering by Joint View Triangulation

Abstract : The creation of novel views using pre-stored images or image-based rendering has many potential applications, such as visual simulation, virtual reality and telepresence, for which traditional computer graphics based on geometric modeling would be unsatisfactory particularly with very complex 3D scenes. This paper presents a new image-based rendering system that tackles the two most difficults problems of image-based modeling: pixel matching and visibility handling. We first introduce the joint view triangulation (JVT), a novel representation for pairs of images that handles the visibility and occlusion problems created by the parallaxes between the images. The joint view triangulation is build from matched planar patches regularized by local smooth constraints encoded by plane homographies. Then, we introduce an incremental edge-constrained construction algorithm. Finally, we present a pseudo-painter's rendering algorithm for the joint view triangulation and demonstrate the performance of these methods experimentally.
Type de document :
Article dans une revue
IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2003, 13, p. 1051-1063
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00118513
Contributeur : Maxime Lhuillier <>
Soumis le : mardi 5 décembre 2006 - 15:39:21
Dernière modification le : mardi 9 octobre 2018 - 09:44:15
Document(s) archivé(s) le : mardi 6 avril 2010 - 19:44:06

Fichiers

Tcsvt03.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00118513, version 1

Citation

Maxime Lhuillier, Long Quan. Image-Based Rendering by Joint View Triangulation. IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2003, 13, p. 1051-1063. 〈hal-00118513〉

Partager

Métriques

Consultations de la notice

144

Téléchargements de fichiers

139