RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

ECCV 2020

doi:10.1007/978-3-030-58536-5_24 /eccv/2020/teed2020eccv-raft/

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.

PDF ECCV Semantic Scholar

Cite

Text

Teed and Deng. "RAFT: Recurrent All-Pairs Field Transforms for Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58536-5_24

Markdown

[Teed and Deng. "RAFT: Recurrent All-Pairs Field Transforms for Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/teed2020eccv-raft/) doi:10.1007/978-3-030-58536-5_24

BibTeX

@inproceedings{teed2020eccv-raft,
  title     = {{RAFT: Recurrent All-Pairs Field Transforms for Optical Flow}},
  author    = {Teed, Zachary and Deng, Jia},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58536-5_24},
  url       = {https://mlanthology.org/eccv/2020/teed2020eccv-raft/}
}