TY - GEN
T1 - RAFT
T2 - 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
AU - Teed, Zachary
AU - Deng, Jia
N1 - Publisher Copyright:
© 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85125453858&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125453858&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85125453858
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 4839
EP - 4843
BT - Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
A2 - Zhou, Zhi-Hua
PB - International Joint Conferences on Artificial Intelligence
Y2 - 19 August 2021 through 27 August 2021
ER -