Abstract
We propose a novel approach for optical flflow estimation, targeted at large displacements with signifificant occlusions. 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 edgeaware geodesic distance. This distance is tailored to handle occlusions and motion boundaries – two common and diffificult issues for optical flflow 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 fifinal flflow estimation. The proposed approach, called Edge-Preserving Interpolation of Correspondences (EpicFlow) is fast and robust to large displacements. It signifificantly outperforms the state of the art on MPI-Sintel and performs on par on Kitti and Middlebury.