Transductive Segmentation of Textured Meshes

Anne-Laure Chauve 1, 2 Jean-Philippe Pons 1, 2 Jean-Yves Audibert 1, 2 Renaud Keriven 1, 2
1 IMAGINE [Marne-la-Vallée]
CSTB - Centre Scientifique et Technique du Bâtiment, LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
2 LIGM - Laboratoire d'Informatique Gaspard-Monge
Abstract : This paper addresses the problem of segmenting a textured mesh into objects or object classes, consistently with user-supplied seeds. We view this task as transductive learning and use the flexibility of kernel-based weights to incorporate a various number of diverse features. Our method combines a Laplacian graph regularizer that enforces spatial coherence in label propagation and an SVM classifier that ensures dissemination of the seeds characteristics. Our interactive framework allows to easily specify classes seeds with sketches drawn on the mesh and potentially refine the segmentation. We obtain qualitatively good segmentations on several architectural scenes and show the applicability of our method to outliers removing.
Type de document :
Communication dans un congrès
9th Asian conference on Computer Vision (ACCV 2009), Sep 2009, Xi'an, China. Springer-Verlag, 5995, pp.502-513, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-12304-7_47〉
Liste complète des métadonnées
https://hal-enpc.archives-ouvertes.fr/hal-00711065
Contributeur : Ist Enpc <>
Soumis le : lundi 25 juin 2012 - 17:07:36
Dernière modification le : jeudi 5 juillet 2018 - 14:23:40
Document(s) archivé(s) le : mercredi 26 septembre 2012 - 02:21:11

Fichier

ACCV09a.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

CSTB | IMAGINE | UNIV-MLV | PARISTECH | LIGM_A3SI | LIGM | ENPC | UPEC | UPEC-UPEM | ESIEE-PARIS

Citation

Anne-Laure Chauve, Jean-Philippe Pons, Jean-Yves Audibert, Renaud Keriven. Transductive Segmentation of Textured Meshes. 9th Asian conference on Computer Vision (ACCV 2009), Sep 2009, Xi'an, China. Springer-Verlag, 5995, pp.502-513, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-12304-7_47〉. 〈hal-00711065〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

413

Téléchargements de fichiers

121

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD