DeepFlow: Large displacement optical flow with deep matching

Philippe Weinzaepfel 1 Jérôme Revaud 1 Zaid Harchaoui 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Optical flow computation is a key component in many computer vision systems designed for tasks such as action detection or activity recognition. However, despite several major advances over the last decade, handling large displacement in optical flow remains an open problem. Inspired by the large displacement optical flow of Brox and Malik, our approach, termed DeepFlow, blends a matching algorithm with a variational approach for optical flow. We propose a descriptor matching algorithm, tailored to the optical flow problem, that allows to boost performance on fast motions. The matching algorithm builds upon a multi-stage architecture with 6 layers, interleaving convolutions and max-pooling, a construction akin to deep convolutional nets. Using dense sampling, it allows to efficiently retrieve quasi-dense correspondences, and enjoys a built-in smoothing effect on descriptors matches, a valuable asset for integration into an energy minimization framework for optical flow estimation. DeepFlow efficiently handles large displacements occurring in realistic videos, and shows competitive performance on optical flow benchmarks. Furthermore, it sets a new state-of-the-art on the MPI-Sintel dataset.
Type de document :
Communication dans un congrès
ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.1385-1392, 2013, 〈10.1109/ICCV.2013.175〉
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00873592
Contributeur : Thoth Team <>
Soumis le : mercredi 16 octobre 2013 - 09:38:57
Dernière modification le : lundi 30 avril 2018 - 15:02:01
Document(s) archivé(s) le : vendredi 17 janvier 2014 - 04:37:27

Fichiers

DeepFlow_iccv2013.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Philippe Weinzaepfel, Jérôme Revaud, Zaid Harchaoui, Cordelia Schmid. DeepFlow: Large displacement optical flow with deep matching. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.1385-1392, 2013, 〈10.1109/ICCV.2013.175〉. 〈hal-00873592〉

Partager

Métriques

Consultations de la notice

11360

Téléchargements de fichiers

17474