GMFlow: Learning Optical Flow via Global Matching. (arXiv:2111.13680v3 [cs.CV] UPDATED)

Learning-based optical flow estimation has been dominated with the pipeline
of cost volume with convolutions for flow regression, which is inherently
limited to local correlations and thus is hard to address the long-standing
challenge of large displacements. To alleviate this, the state-of-the-art
framework RAFT gradually improves its prediction quality by using a large
number of iterative refinements, achieving remarkable performance but
introducing linearly increasing inference time. To enable both high accuracy
and efficiency, we completely revamp the dominant flow regression …

arxiv cv flow global learning