A Fusion Approach for Multi-Frame Optical Flow Estimation
This addresses the problem of improving optical flow accuracy for computer vision applications, representing an incremental advance over existing methods.
The paper tackles optical flow estimation by using more than two consecutive frames, achieving state-of-the-art results with a fusion approach that ranks first on MPI Sintel and KITTI 2015 benchmarks.
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.