Dense Segmentation-aware Descriptors

Abstract : In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor's center, as suggested by soft segmentation masks. Our treatment is applicable to any image point, i.e. dense, and its computational overhead is in the order of a few seconds. We integrate this idea with Dense SIFT, and also with Dense Scale and Rotation Invariant Descriptors (SID), delivering descriptors that are densely computable, invariant to scaling and rotation, and robust to background changes. We apply our approach to standard benchmarks on large displacement motion estimation using SIFT-flow and wide-baseline stereo, systematically demonstrating that the introduction of segmentation yields clear improvements.
Type de document :
Communication dans un congrès
Computer Vision and Pattern Recognition, Jun 2013, Portland, Oregon, United States. 2013
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00856023
Contributeur : Eduard Trulls Fortuny <>
Soumis le : vendredi 30 août 2013 - 14:37:00
Dernière modification le : jeudi 29 mars 2018 - 13:36:02
Document(s) archivé(s) le : jeudi 6 avril 2017 - 11:02:14

Fichier

cvpr13-final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00856023, version 1

Collections

Citation

Eduard Trulls, Iasonas Kokkinos, Alberto Sanfeliu, Francesc Moreno-Noguer. Dense Segmentation-aware Descriptors. Computer Vision and Pattern Recognition, Jun 2013, Portland, Oregon, United States. 2013. 〈hal-00856023〉

Partager

Métriques

Consultations de la notice

271

Téléchargements de fichiers

407