FALDOI: A new minimization strategy for large displacement variational optical flow
This work addresses the challenge of capturing large displacements in optical flow for computer vision applications, representing an incremental improvement over existing variational methods.
The authors tackled the problem of large displacement optical flow by introducing a new minimization strategy that uses sparse matches to guide a structured coordinate-descent, resulting in robust performance against outliers and noise. The method consistently outperforms coarse-to-fine approaches on standard benchmarks with good qualitative and quantitative results.
We propose a large displacement optical flow method that introduces a new strategy to compute a good local minimum of any optical flow energy functional. The method requires a given set of discrete matches, which can be extremely sparse, and an energy functional which locally guides the interpolation from those matches. In particular, the matches are used to guide a structured coordinate-descent of the energy functional around these keypoints. It results in a two-step minimization method at the finest scale which is very robust to the inevitable outliers of the sparse matcher and able to capture large displacements of small objects. Its benefits over other variational methods that also rely on a set of sparse matches are its robustness against very few matches, high levels of noise and outliers. We validate our proposal using several optical flow variational models. The results consistently outperform the coarse-to-fine approaches and achieve good qualitative and quantitative performance on the standard optical flow benchmarks.