Saved in:
Bibliographic Details
Main Authors: Wang, Yihan, Deng, Jia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.24836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908920072634368
author Wang, Yihan
Deng, Jia
author_facet Wang, Yihan
Deng, Jia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24836
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
Wang, Yihan
Deng, Jia
Computer Vision and Pattern Recognition
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.
title WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.24836