WAFT: Warping-Alone Field Transforms for Optical Flow
Abstract
WAFT replaces cost volumes with high-resolution warping for optical flow estimation, improving accuracy and speed across major benchmarks.
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 https://github.com/princeton-vl/WAFT{https://github.com/princeton-vl/WAFT}.
Get this paper in your agent:
hf papers read 2506.21526 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 4
LibreYOLO/LibreWAFTt-flow-dinov3
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper