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

TL;DR

This paper introduces a large-scale pre-training framework for cross-modality image matching, enabling models to generalize across diverse imaging modalities and outperform existing methods in multiple unseen tasks.

Contribution

The authors propose a synthetic cross-modal training approach that significantly improves the generalization of image matching models across various modalities.

Findings

Model trained with our framework generalizes well to over eight unseen cross-modality tasks.

Our approach outperforms existing generalization and task-specific methods.

The method enhances multi-modality analysis in scientific and AI applications.

Abstract

Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image matching algorithms have dramatically outperformed humans in rapidly and accurately finding large amounts of correspondences. However, when dealing with images captured under different imaging modalities that result in significant appearance changes, the performance of these algorithms often deteriorates due to the scarcity of annotated cross-modal training data. This limitation hinders applications in various fields that rely on multiple image modalities to obtain complementary information. To address this challenge, we propose a large-scale pre-training framework that utilizes synthetic cross-modal training signals, incorporating diverse data from various sources, to train models to recognize and match fundamental structures across images. This capability is transferable to real-world, unseen cross-modality image matching tasks. Our key finding is that the matching model trained with our framework achieves remarkable generalizability across more than eight unseen cross-modality registration tasks using the same network weight, substantially outperforming existing methods, whether designed for generalization or tailored for specific tasks. This advancement significantly enhances the applicability of image matching technologies across various scientific disciplines and paves the way for new applications in multi-modality human and artificial intelligence analysis and beyond.