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 2.3x
faster than existing methods while maintaining competitive performance. The
code is publicly available at this https URL

SEA-RAFT 是一种更简单、高效、准确的用于光流的 RAFT 算法，通过采用混合拉普拉斯损失函数进行训练，直接回归初始光流以提高收敛速度，并引入刚性运动预训练以提升泛化性能。在 Spring 基准测试中，SEA-RAFT 以 3.69 的端点错误（EPE）和 0.36 的像素异常率（1px）取得了最先进的准确性，相较于最佳发布结果减少了 22.9% 和 17.8% 的误差。此外，SEA-RAFT 实现了在 KITTI 和 Spring 数据集上最好的跨数据集泛化性能。尽管保持了竞争性能，但 SEA-RAFT 至少比现有方法快 2.3 倍。代码可以从此 https URL 进行公开获取。