SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
Abstract
We introduce SEA-RAFT, a more simple, efficient, and accurate RAFT for optical flow. Compared with RAFT, SEA-RAFT is trained with a new loss (mixture of Laplace). It directly regresses an initial flow for faster convergence in iterative refinements and introduces rigid-motion pre-training to improve generalization. SEA-RAFT achieves state-of-the-art accuracy on the Spring benchmark with a 3.69 endpoint-error (EPE) and a 0.36 1-pixel outlier rate (1px), representing 22.9% and 17.8% error reduction from best published results. In addition, SEA-RAFT obtains the best cross-dataset generalization on KITTI and Spring. With its high efficiency, SEA-RAFT operates at least 2.3× faster than existing methods while maintaining competitive performance. The code is publicly available at https://github.com/princeton-vl/SEA-RAFT.
Cite
Text
Wang et al. "SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72667-5_3Markdown
[Wang et al. "SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/wang2024eccv-searaft/) doi:10.1007/978-3-031-72667-5_3BibTeX
@inproceedings{wang2024eccv-searaft,
title = {{SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow}},
author = {Wang, Yihan and Lipson, Lahav O and Deng, Jia},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72667-5_3},
url = {https://mlanthology.org/eccv/2024/wang2024eccv-searaft/}
}