FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation
This work provides incremental improvements for applications requiring precise motion estimation, such as in robotics or video analysis.
The paper tackled the problem of improving optical flow accuracy by addressing interpolation weaknesses in the Flow Field algorithm, achieving top results on KITTI and MPI Sintel benchmarks.
Optical Flow algorithms are of high importance for many applications. Recently, the Flow Field algorithm and its modifications have shown remarkable results, as they have been evaluated with top accuracy on different data sets. In our analysis of the algorithm we have found that it produces accurate sparse matches, but there is room for improvement in the interpolation. Thus, we propose in this paper FlowFields++, where we combine the accurate matches of Flow Fields with a robust interpolation. In addition, we propose improved variational optimization as post-processing. Our new algorithm is evaluated on the challenging KITTI and MPI Sintel data sets with public top results on both benchmarks.