# Joint Optical Flow and Temporally Consistent Semantic Segmentation Source: [Joint Optical Flow and Temporally Consistent Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:23:26.300Z Authors: Junhwa Hur, Stefan Roth Published: 2016-07-26T14:25:37.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Optical Flow on KITTI 2015 (test)](): Optical Flow; KITTI 2015 (test); Fl Error (All): 16.47. ## Original sources and implementation [Original paper]() [PDF]()