EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow

TL;DR

EpicFlow introduces an edge-aware interpolation method for optical flow that effectively handles large displacements and occlusions, combining sparse matching with variational refinement for fast, accurate results.

Contribution

It presents a novel edge-preserving interpolation technique using geodesic distance, improving optical flow estimation especially in challenging scenarios with occlusions.

Findings

Outperforms state-of-the-art on MPI-Sintel dataset

Achieves comparable results on Kitti and Middlebury datasets

Fast and robust to large displacements

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.