A Fusion Approach for Multi-Frame Optical Flow Estimation
2019 IEEE Winter Conference on Applications of Computer Vision (WACV)(2018)
摘要
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.
更多查看译文
关键词
Multi-frame optical flow, Temporal optical flow fusion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络