SuperPatchMatch: an Algorithm for Robust Correspondences of Superpixel Patches

Abstract : Superpixels have become very popular in many computer vision applications. Nevertheless, their use remains under-exploited since the superpixel decomposition may produce irregular and non stable segmentation result due to the dependency of such methods to the image content. In this paper, we first introduce a novel structure, a superpixel-based patch, called SuperPatch. The proposed structure, based on superpixel neighborhood, leads to a robust descriptor since spatial information is naturally included. The generalization of the PatchMatch correspondence method to these SuperPatches, named SuperPatchMatch, is next proposed. Image segmentation and labeling experiments show the potential of our approach, since we obtain very competitive results compared to the state-of-the-art methods.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01432116
Contributeur : Rémi Giraud <>
Soumis le : mercredi 11 janvier 2017 - 15:20:31
Dernière modification le : samedi 14 janvier 2017 - 01:05:36

Fichier

Giraud_SPM_2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01432116, version 1

Collections

Citation

Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis. SuperPatchMatch: an Algorithm for Robust Correspondences of Superpixel Patches. 2017. <hal-01432116>

Partager

Métriques

Consultations de
la notice

90

Téléchargements du document

89