SceneFlowFields: Dense Interpolation of Sparse Scene Flow Correspondences

TL;DR

This paper introduces a novel scene flow estimation method that uses dense interpolation of sparse matches, combined with edge-preserving techniques and optional ego-motion modeling, achieving competitive results on benchmark datasets.

Contribution

It is the first to demonstrate scene flow estimation through dense interpolation of sparse matches without prior regularization, incorporating edge information and optional ego-motion modeling.

Findings

Achieves competitive results on KITTI benchmark.

Outperforms state-of-the-art on MPI Sintel.

Effective scene segmentation into static and dynamic parts.

Abstract

While most scene flow methods use either variational optimization or a strong rigid motion assumption, we show for the first time that scene flow can also be estimated by dense interpolation of sparse matches. To this end, we find sparse matches across two stereo image pairs that are detected without any prior regularization and perform dense interpolation preserving geometric and motion boundaries by using edge information. A few iterations of variational energy minimization are performed to refine our results, which are thoroughly evaluated on the KITTI benchmark and additionally compared to state-of-the-art on MPI Sintel. For application in an automotive context, we further show that an optional ego-motion model helps to boost performance and blends smoothly into our approach to produce a segmentation of the scene into static and dynamic parts.