DeepFlow: Large displacement optical flow with deep matching - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

DeepFlow: Large displacement optical flow with deep matching

Philippe Weinzaepfel
  • Fonction : Auteur
  • PersonId : 962585
Jérôme Revaud
  • Fonction : Auteur
  • PersonId : 946914
Zaid Harchaoui
  • Fonction : Auteur
  • PersonId : 895242
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

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.
Fichier principal
Vignette du fichier
DeepFlow_iccv2013.pdf (7.65 Mo) Télécharger le fichier
Vignette du fichier
recur_left.png (75.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-00873592 , version 1 (16-10-2013)

Identifiants

Citer

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. pp.1385-1392, ⟨10.1109/ICCV.2013.175⟩. ⟨hal-00873592⟩
12884 Consultations
15710 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More