WAFT: Warping-Alone Field Transforms for Optical Flow
About
We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow. WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accuracy with lower memory cost. This design challenges the conventional wisdom that constructing cost volumes is necessary for strong performance. WAFT is a simple and flexible meta-architecture with minimal inductive biases and reliance on custom designs. Compared with existing methods, WAFT ranks 1st on Spring, Sintel, and KITTI benchmarks, achieves the best zero-shot generalization on KITTI, while being 1.3-4.1x faster than existing methods that have competitive accuracy (e.g., 1.3x than Flowformer++, 4.1x than CCMR+). Code and model weights are available at \href{https://github.com/princeton-vl/WAFT}{https://github.com/princeton-vl/WAFT}.