RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

Zachary Teed; Jia Deng

ECCV 2020poster3178 citations

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

Abstract

We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for estimating optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance on both KITTI and Sintel, with strong cross-dataset generalization and high efficiency in inference time, training speed, and parameter count. "

BibTeX

@inproceedings{eccv2020_raftrecurrentall,
  title = {RAFT: Recurrent All-Pairs Field Transforms for Optical Flow},
  author = {Zachary Teed and Jia Deng},
  booktitle = {ECCV 2020},
  year = {2020}
}