Towards Skeleton based Reconstruction : From Projective Skeletonization to Canal Surface Estimation

Abstract : We present a novel approach to reconstruct a 3D object from images corresponding to two different viewpoints: we estimate the skeleton of the object instead of its surface. The originality of the method is to be able to reconstruct a tubular object with a limited number of input images. Unlike classical reconstruction methods, like multi-view stereo or more recently structure-from-motion, this approach does not rely on interest points but estimates the topology of the object and derives its surface. Our contribution are twofold. First, given two perspective images of the 3D shape, the projection of the skeleton is computed in 2D. Secondly the 3D skeleton is reconstructed from the two projections using triangulation and matching. A mesh is finally derived for each skeleton branch.
Type de document :
Communication dans un congrès
International Conference on 3D Vision (3DV 2015), Oct 2015, Lyon, France. Proceedings of 3DV 2015, pp. 545-553, 2015
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01272139
Contributeur : Open Archive Toulouse Archive Ouverte (oatao) <>
Soumis le : mercredi 10 février 2016 - 11:49:43
Dernière modification le : samedi 13 février 2016 - 01:11:00
Document(s) archivé(s) le : samedi 12 novembre 2016 - 16:58:16

Fichier

durix_15076.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01272139, version 1
  • OATAO : 15076

Collections

Citation

Bastien Durix, Géraldine Morin, Sylvie Chambon, Céline Roudet, Lionel Garnier. Towards Skeleton based Reconstruction : From Projective Skeletonization to Canal Surface Estimation. International Conference on 3D Vision (3DV 2015), Oct 2015, Lyon, France. Proceedings of 3DV 2015, pp. 545-553, 2015. <hal-01272139>

Partager

Métriques

Consultations de
la notice

33

Téléchargements du document

33