EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
This addresses optical flow estimation for computer vision applications, offering a fast and robust method for handling large displacements and occlusions, with incremental improvements in specific benchmarks.
The paper tackles optical flow estimation for large displacements with occlusions by proposing EpicFlow, which uses edge-preserving interpolation from sparse matches and variational minimization. It significantly outperforms state-of-the-art on MPI-Sintel and performs competitively on Kitti and Middlebury.
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.