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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [38 references]  Display  Hide  Download


https://hal.inria.fr/hal-01142656
Contributor : Thoth Team <>
Submitted on : Wednesday, April 15, 2015 - 4:40:46 PM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Document(s) archivé(s) le : Tuesday, April 18, 2017 - 8:40:44 PM

Files

cvpr15_epicflow.pdf
Publisher files allowed on an open archive

Identifiers

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. pp.1164-1172, ⟨10.1109/CVPR.2015.7298720⟩. ⟨hal-01142656⟩

Share

Metrics

Record views

16581

Files downloads

11182