EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2015

EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow

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

Résumé

We propose a novel approach for optical flow estima-tion, targeted at large displacements with significant oc-clusions. It consists of two steps: i) dense matching by edge-preserving interpolation from a sparse set of matches; ii) variational energy minimization initialized with the dense matches. The sparse-to-dense interpolation relies on an appropriate choice of the distance, namely an edge-aware geodesic distance. This distance is tailored to han-dle occlusions and motion boundaries, two common and difficult issues for optical flow computation. We also pro-pose an approximation scheme for the geodesic distance to allow fast computation without loss of performance. Sub-sequent to the dense interpolation step, standard one-level variational energy minimization is carried out on the dense matches to obtain the final flow estimation. The proposed approach, called Edge-Preserving Interpolation of Corre-spondences (EpicFlow) is fast and robust to large displace-ments. It significantly outperforms the state of the art on MPI-Sintel and performs on par on KITTI and Middlebury.
Fichier principal
Vignette du fichier
epicflow.pdf (2.69 Mo) Télécharger le fichier
Vignette du fichier
contour_boundaries_temple_3_31.jpg (23.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01097477 , version 1 (13-01-2015)
hal-01097477 , version 2 (27-04-2015)

Identifiants

Citer

Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. 2015. ⟨hal-01097477v1⟩
2760 Consultations
6084 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More