LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation, ECCV 2020
(1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.
Code : https://github.com/twhui/LiteFlowNet3