FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation

TL;DR

FlowFields++ enhances optical flow estimation by combining accurate sparse matches with robust interpolation and improved optimization, achieving top results on KITTI and MPI Sintel benchmarks.

Contribution

It introduces FlowFields++, a novel method that integrates accurate matching with robust interpolation and improved variational optimization for better optical flow accuracy.

Findings

Achieves top accuracy on KITTI dataset.

Sets new state-of-the-art results on MPI Sintel.

Demonstrates robustness across challenging data sets.

Abstract

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.