Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow

• An occlusion-aware optical flow estimation based on a discrete aggregation framework.
• Accurate parametric patch-based scheme for motion candidate computation with an efficient integration of feature matching.
• A generic exemplar-based approach for recovering motion in occluded regions.
• Joint motion field and occlusion map estimation guided by an occlusion confidence map obtained from motion candidates.
• State-of-the-art results on the challenging MPI Sintel dataset for large displacements and occlusions.

Handling all together large displacements, motion details and occlusions remains an open issue for reliable computation of optical flow in a video sequence. We propose a two-step aggregation paradigm to address this problem. The idea is to supply local motion candidates at every pixel in a first step, and then to combine them to determine the global optical flow field in a second step. We exploit local parametric estimations combined with patch correspondences and we experimentally demonstrate that they are sufficient to produce highly accurate motion candidates. The aggregation step is designed as the discrete optimization of a global regularized energy. The occlusion map is estimated jointly with the flow field throughout the two steps. We propose a generic exemplar-based approach for occlusion filling with motion vectors. We achieve state-of-the-art results in the MPI-Sintel benchmark, with particularly significant improvements in the case of large displacements and occlusions.