EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow

(1) , (1) , (1) , (1)
1

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.
Vignette du fichier
cvpr15_epicflow.jpg (14.06 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
cvpr15_epicflow.pdf (4.76 Mo) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01142656 , version 1 (15-04-2015)

Identifiers

Cite

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⟩
5953 View
7682 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More