Joint Optical Flow and Temporally Consistent Semantic Segmentation
This addresses the problem of improving visual scene understanding for autonomous systems by integrating two key tasks, though it appears incremental as it builds on existing methods.
The paper tackles the joint estimation of optical flow and temporally consistent semantic segmentation by leveraging their mutual benefits, achieving state-of-the-art optical flow results and outperforming all published algorithms on dynamic objects in the KITTI benchmark.
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.