Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow
This work addresses the problem of reliable optical flow estimation for computer vision applications, offering incremental improvements in handling large displacements and occlusions.
The paper tackles the challenge of computing optical flow in video sequences, especially for large displacements and occlusions, by proposing a two-step aggregation paradigm that combines local motion candidates and achieves state-of-the-art results with significant improvements in these difficult cases.
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 computer vision benchmarks, with particularly significant improvements in the case of large displacements and occlusions.