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 complete tubular 3D object from only two input images. Unlike classical reconstruction methods like multiview stereo, this approach does not rely on interest points but estimates the topology of the object and derives its surface. Our contributions are twofold. First, given two perspective images of the 3D shape, the projection of the skeleton is computed in 2D. Second 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
3DV (The 3rd international conference on 3D Vision), Oct 2015, Lyon, France
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01213239
Contributeur : Bastien Durix <>
Soumis le : mardi 15 décembre 2015 - 14:49:30
Dernière modification le : jeudi 17 décembre 2015 - 01:05:58
Document(s) archivé(s) le : samedi 29 avril 2017 - 15:10:27

Fichier

2015_Durix_preprint.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01213239, version 1

Collections

Citation

Bastien Durix, Géraldine Morin, Sylvie Chambon, Céline Roudet, Lionel Garnier. Towards Skeleton based Reconstruction: From Projective Skeletonization to Canal Surface Estimation. 3DV (The 3rd international conference on 3D Vision), Oct 2015, Lyon, France. <hal-01213239>

Partager

Métriques

Consultations de
la notice

110

Téléchargements du document

35