Distortion driven variational multi-view reconstruction

Patricio Alejandro Galindo 1 Rhaleb Zayer 1
1 ALICE - Geometry and Lighting
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper revisits variational multi-view stereo and identifies two issues pertaining to matching and view merging: i) regions with low visibility and relatively high depth variation are only resolved by the sole regularizer contribution. This often induces wrong matches which tend to bleed into neighboring regions, and more importantly distort nearby features. ii) small matching errors can lead to overlapping surface layers which cannot be easily addressed by standard outlier removal techniques. In both scenarios, we rely on the analysis of the distortion of spatial and planar maps in order to improve the quality of the reconstruction. At the matching level, an anisotropic diffusion driven by spatial grid distortion is proposed to steer grid lines away from those problematic regions. At the merging level, advantage is taken of Lambert's cosine law to favor contributions from image areas where the cosine angle between the surface normal and the line of sight is maximal. Tests on standard benchmarks suggest a good blend between computational efficiency, ease of implementation, and reconstruction quality.
Type de document :
Communication dans un congrès
Proceedings on International Conference in 3D Vision (3DV), Dec 2014, Tokyo, Japan. 2014
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01088428
Contributeur : Patricio Galindo <>
Soumis le : jeudi 27 novembre 2014 - 23:04:10
Dernière modification le : jeudi 11 janvier 2018 - 06:20:18
Document(s) archivé(s) le : lundi 2 mars 2015 - 09:31:53

Fichier

distortion-driven_variational_...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01088428, version 1

Collections

Citation

Patricio Alejandro Galindo, Rhaleb Zayer. Distortion driven variational multi-view reconstruction. Proceedings on International Conference in 3D Vision (3DV), Dec 2014, Tokyo, Japan. 2014. 〈hal-01088428〉

Partager

Métriques

Consultations de la notice

145

Téléchargements de fichiers

71