We introduce WAFT-Stereo, a simple and effective warping-based method for stereo matching. WAFT-Stereo demonstrates that cost volumes, a common design used in many leading methods, are not necessary for strong performance and can be replaced by warping with improved efficiency. WAFT-Stereo ranks first on ETH3D (BP-0.5), Middlebury (RMSE), and KITTI (all metrics), reducing the zero-shot error by 81% on ETH3D, while being 1.8-6.7x faster than competitive methods. Code and model weights are available at https://github.com/princeton-vl/WAFT-Stereo.
Cite
@article{arxiv.2603.24836,
title = {WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching},
author = {Yihan Wang and Jia Deng},
journal= {arXiv preprint arXiv:2603.24836},
year = {2026}
}