MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training

Project Page | Paper

MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
Xingyi He, Hao Yu, Sida Peng, Dongli Tan, Zehong Shen, Hujun Bao†, Xiaowei Zhou†
TPAMI 2026

 ![animated](video/teaser_demo.gif) 

Quick Start

HuggingFace demo for MatchAnything

Models are on HuggingFace! (Pre-trained weights are included) The training code will be available later.

Citation

@inproceedings{he2025matchanything,
title={MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training},
author={He, Xingyi and Yu, Hao and Peng, Sida and Tan, Dongli and Shen, Zehong and Bao, Hujun and Zhou, Xiaowei},
booktitle={Arxiv},
year={2025}
}