SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches

Abstract : Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency 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 method to SuperPatches, named SuperPatchMatch, is introduced. Finally, we propose a framework to perform fast segmentation and labeling from an image database, and demonstrate the potential of our approach since we outperform, in terms of computational cost and accuracy, the results of state-of-the-art methods on both face labeling and medical image segmentation.
Type de document :
Article dans une revue
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2017, <10.1109/TIP.2017.2708504>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01432116
Contributeur : Rémi Giraud <>
Soumis le : vendredi 9 juin 2017 - 00:42:31
Dernière modification le : mardi 13 juin 2017 - 01:07:00

Fichier

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

Identifiants

Collections

Citation

Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis. SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2017, <10.1109/TIP.2017.2708504>. <hal-01432116v3>

Partager

Métriques

Consultations de
la notice

38

Téléchargements du document

39