WAFT-Stereo：基于纯形变场的立体匹配变换方法

WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching

March 25, 2026

作者: Yihan Wang, Jia Deng

cs.AI

摘要

我们提出WAFT-Stereo，一种基于形变操作的简易高效立体匹配方法。该方法证明了许多主流方法常用的代价体积设计并非实现优异性能的必要条件，通过形变操作替代该模块可显著提升效率。WAFT-Stereo在ETH3D、KITTI和Middlebury公开基准测试中均位列第一，在ETH3D基准上的零样本误差降低81%，同时运算速度比竞品方法快1.8-6.7倍。代码与模型权重已开源：https://github.com/princeton-vl/WAFT-Stereo。

English

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, KITTI and Middlebury public benchmarks, reducing the zero-shot error by 81% on ETH3D benchmark, while being 1.8-6.7x faster than competitive methods. Code and model weights are available at https://github.com/princeton-vl/WAFT-Stereo.