Light Field Segmentation Using a Ray-Based Graph Structure

Matthieu Hog 1, 2 Neus Sabater 1 Christine Guillemot 2
2 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : In this paper, we introduce a novel graph representation for interactive light eld segmentation using Markov Random Field (MRF). The greatest barrier to the adoption of MRF for light eld processing is the large volume of input data. The proposed graph structure exploits the redundancy in the ray space in order to reduce the graph size, decreasing the running time of MRF-based optimisation tasks. Concepts of free rays and ray bundles with corresponding neighbourhood relationships are de- ned to construct the simpli ed graph-based light eld representation. We then propose a light eld interactive segmentation algorithm using graph-cuts based on such ray space graph structure, that guarantees the segmentation consistency across all views. Our experiments with several datasets show results that are very close to the ground truth, competing with state of the art light eld segmentation methods in terms of accuracy and with a signi cantly lower complexity. They also show that our method performs well on both densely and sparsely sampled light fields.
Type de document :
Communication dans un congrès
European Conference on Computer Vision - ECCV, Oct 2016, Amsterdam, Netherlands. pp.16, 2016
Liste complète des métadonnées

Littérature citée [41 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01388965
Contributeur : Christine Guillemot <>
Soumis le : mardi 15 novembre 2016 - 10:39:14
Dernière modification le : mercredi 16 mai 2018 - 11:23:38
Document(s) archivé(s) le : jeudi 16 mars 2017 - 16:32:10

Fichier

LF_segmentation-accepted.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01388965, version 1

Citation

Matthieu Hog, Neus Sabater, Christine Guillemot. Light Field Segmentation Using a Ray-Based Graph Structure. European Conference on Computer Vision - ECCV, Oct 2016, Amsterdam, Netherlands. pp.16, 2016. 〈hal-01388965〉

Partager

Métriques

Consultations de la notice

400

Téléchargements de fichiers

245