EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow

Jerome Revaud 1 Philippe Weinzaepfel 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 : We propose a novel approach for optical flow estimation , 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 handle occlusions and motion boundaries – two common and difficult issues for optical flow computation. We also propose an approximation scheme for the geodesic distance to allow fast computation without loss of performance. Subsequent 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 Correspondences (EpicFlow) is fast and robust to large displacements. It significantly outperforms the state of the art on MPI-Sintel and performs on par on Kitti and Middlebury.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. Proceedings IEEE Conference on Computer Vision & Pattern Recognition
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-01142656
Contributeur : Thoth Team <>
Soumis le : mercredi 15 avril 2015 - 16:40:46
Dernière modification le : vendredi 11 août 2017 - 11:54:09
Document(s) archivé(s) le : mardi 18 avril 2017 - 20:40:44

Fichiers

cvpr15_epicflow.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01142656, version 1

Collections

Citation

Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. Proceedings IEEE Conference on Computer Vision & Pattern Recognition. 〈hal-01142656〉

Partager

Métriques

Consultations de
la notice

15195

Téléchargements du document

8827