Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow

Abstract : Handling all together large displacements, motion details and occlusions remains an open issue for reliable computation of optical flow in a video sequence. We propose a two-step aggregation paradigm to address this problem. The idea is to supply local motion candidates at every pixel in a first step, and then to combine them to determine the global optical flow field in a second step. We exploit local parametric estimations combined with patch correspondences and we experimentally demonstrate that they are sufficient to produce highly accurate motion candidates. The aggregation step is designed as the discrete optimization of a global regularized energy. The occlusion map is estimated jointly with the flow field throughout the two steps. We propose a generic exemplar-based approach for occlusion filling with motion vectors. We achieve state-of-the-art results in computer vision benchmarks, with particularly significant improvements in the case of large displacements and occlusions.
Type de document :
Article dans une revue
Computer Vision and Image Understanding, Elsevier, 2016, pp.17. 〈10.1016/j.cviu.2015.11.020〉
Liste complète des métadonnées

Littérature citée [90 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01001758
Contributeur : Denis Fortun <>
Soumis le : mardi 22 décembre 2015 - 15:19:43
Dernière modification le : jeudi 7 janvier 2016 - 13:35:02
Document(s) archivé(s) le : dimanche 30 avril 2017 - 00:06:27

Fichier

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

Identifiants

Collections

Citation

Denis Fortun, Patrick Bouthemy, Charles Kervrann. Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow. Computer Vision and Image Understanding, Elsevier, 2016, pp.17. 〈10.1016/j.cviu.2015.11.020〉. 〈hal-01001758v2〉

Partager

Métriques

Consultations de la notice

164

Téléchargements de fichiers

90