Joint Optical Flow and Temporally Consistent Semantic Segmentation

TL;DR

This paper introduces a joint method for optical flow and semantic segmentation that mutually enhances both tasks, achieving state-of-the-art results on the KITTI benchmark especially for dynamic objects.

Contribution

It presents a novel joint estimation approach that leverages semantic segmentation to improve optical flow accuracy and vice versa, demonstrating significant performance gains.

Findings

Achieves state-of-the-art optical flow results on KITTI.

Outperforms existing methods on dynamic objects.

Demonstrates mutual benefits of joint estimation.

Abstract

The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems. Consequently, there has been a large amount of research dedicated to semantic segmentation and dense motion estimation. In this paper, we propose a method for jointly estimating optical flow and temporally consistent semantic segmentation, which closely connects these two problem domains and leverages each other. Semantic segmentation provides information on plausible physical motion to its associated pixels, and accurate pixel-level temporal correspondences enhance the accuracy of semantic segmentation in the temporal domain. We demonstrate the benefits of our approach on the KITTI benchmark, where we observe performance gains for flow and segmentation. We achieve state-of-the-art optical flow results, and outperform all published algorithms by a large margin on challenging, but crucial dynamic objects.