RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
Zachary Teed,Jia Deng
TLDR
Recurrent All-Pairs Field Transforms achieves state-of-the-art performance on the KITTI and Sintel datasets and has strong cross-dataset generalization as well as high efficiency in inference time, training speed, and parameter count.
Abstract
We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for 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 the KITTI and Sintel datasets. In addition, RAFT has strong cross-dataset generalization as well as high efficiency in inference time, training speed, and parameter count.