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 :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-01097477
Contributor : Thoth Team <>
Submitted on : Monday, April 27, 2015 - 11:02:11 AM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on : Wednesday, April 19, 2017 - 7:14:36 AM

Files

epicflow.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01097477, version 2
  • ARXIV : 1501.02565

Collections

Citation

Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. 2015. ⟨hal-01097477v2⟩

Share

Metrics

Record views

10064

Files downloads

5735