Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Skeleton-Based Multiview Reconstruction

Bastien Durix 1, * Géraldine Morin 1, * Sylvie Chambon 1, * Céline Roudet 2, * Lionel Garnier 2, *
* Auteur correspondant
1 IRIT-REVA - Real Expression Artificial Life
IRIT - Institut de recherche en informatique de Toulouse
Abstract : The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose topology is a tree) from the perspective skeletons on an arbitrary number of calibrated acquisitions. The main contribution is to estimate the 3D skeleton, from multiple images: its topology is chosen as the closest to those of the perspective skeletons on the set of images, which means that the number of topology changes to map the 3D skeleton topology to topologies on images is minimum. This way, the number of matched branches is maximum.
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01464056
Contributeur : Le2i - Université de Bourgogne <>
Soumis le : jeudi 9 février 2017 - 19:15:11
Dernière modification le : vendredi 17 juillet 2020 - 14:54:11

Identifiants

  • HAL Id : hal-01464056, version 1

Citation

Bastien Durix, Géraldine Morin, Sylvie Chambon, Céline Roudet, Lionel Garnier. Skeleton-Based Multiview Reconstruction. 23rd IEEE International Conference on Image Processing (ICIP), Sep 2016, Phoenix, AZ, United States. pp.4047-4051. ⟨hal-01464056⟩

Partager

Métriques

Consultations de la notice

295