Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
This work addresses the challenge of accurate optical flow estimation for computer vision applications, offering a novel method that enhances existing state-of-the-art techniques with measurable gains.
The paper tackles the problem of large displacement optical flow estimation by introducing a dense correspondence field approach that reduces outliers compared to approximate nearest neighbor fields, resulting in significant performance improvements over EpicFlow on MPI-Sintel, KITTI, and Middlebury benchmarks.
Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the major disadvantage of being very outlier prone as they are not designed to find the optical flow, but the visually most similar correspondence. In this paper we present a dense correspondence field approach that is much less outlier prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields. Our approach is conceptually novel as it does not require explicit regularization, smoothing (like median filtering) or a new data term, but solely our novel purely data based search strategy that finds most inliers (even for small objects), while it effectively avoids finding outliers. Moreover, we present novel enhancements for outlier filtering. We show that our approach is better suited for large displacement optical flow estimation than state-of-the-art descriptor matching techniques. We do so by initializing EpicFlow (so far the best method on MPI-Sintel) with our Flow Fields instead of their originally used state-of-the-art descriptor matching technique. We significantly outperform the original EpicFlow on MPI-Sintel, KITTI and Middlebury.