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/SEARAFT.
Loading