SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
This improves optical flow estimation for computer vision applications, but it is incremental as it builds on the RAFT framework.
The paper tackles optical flow estimation by introducing SEA-RAFT, which achieves state-of-the-art accuracy on the Spring benchmark with a 3.69 endpoint-error and 0.36 1-pixel outlier rate, representing 22.9% and 17.8% error reductions, and operates at least 2.3x faster than existing methods.
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 https://github.com/princeton-vl/SEA-RAFT.