2018/10/23 by Zhile Ren, Orazio Gallo, Ren, Zhile +10 · 2 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.1810.10066
Work accepted at IEEE Winter Conference on Applications of Computer Vision (WACV 2019)
openalex publication_date 2018/10/23 · arxiv created 2018/11/29 · arxiv updated 2018/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present a simple, yet effective fusion approach for multi-frame optical flow that benefits from longer-term temporal cues. Our method first warps the optical flow from previous frames to the current, thereby yielding multiple plausible estimates. It then fuses the complementary information carried by these estimates into a new optical flow field. At the time of writing, our method ranks first among published results in the MPI Sintel and KITTI 2015 benchmarks. Our models will be available on https://github.com/NVlabs/PWC-Net.