WAFT: Warping-Alone Field Transforms for Optical Flow

Yihan Wang, Jia Deng

Keywords: Optical Flow; Computer Vision; Warping; Dense Correspondences

Abstract:

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 nec-
essary 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 up to 4.1× faster
than methods with similar performance. Code and model weights will be available
upon acceptance.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 2912