Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images

About

Multi-modal image matching is essential for visual localization and multi-sensor fusion, but it is hindered by the scarcity of large-scale training data with precise geometric annotations. Existing real-world datasets suffer from prohibitive costs, limited scene diversity, and errors in SfM-MVS pipelines, while synthetic methods struggle to maintain 3D geometric consistency or achieve photorealistic appearance. To address this, we propose AnyMatch, a novel framework that leverages abundant, easily accessible single-view images at minimal cost to generate rich multi-modal training data. AnyMatch integrates monocular depth estimation, 3D reprojection, diffusion-based inpainting, and crossmodal image translation to synthesize multi-view, multi-modal image pairs with 3D geometric fidelity. Crucially, our method provides annotations that strictly adhere to 3D geometric consistency through explicit 3D reprojection, avoiding SfM-MVS error accumulation. Furthermore, AnyMatch offers strong scalability, enabling controllable scene diversity and annotation difficulty via adjustable input and camera parameters. We construct Any-syn, a large-scale synthetic multi-modal dataset using AnyMatch. Experimental results show that matching networks (e.g., LoFTR, EDM, RoMa) fine-tuned on Any-syn achieve substantial performance gains on multi-modal benchmarks, exhibiting superior generalization and robustness compared to models trained on existing data.

Meng Yang, Zizhuo Li, Linfeng Tang, Fan Fan, Jiayi Ma• 2026

Related benchmarks

TaskDatasetResultRank
Homography EstimationDIODE RGB-Depth (test)
AUC @ 3px29.77
13
Homography EstimationDIODE RGB-Normal (test)
AUC @ 3px39.26
13
Homography EstimationDSEC RGB-Event (test)
AUC @ 3px60
13
Image MatchingMedical Retina (test)
AUC @ 3px Tolerance39.76
13
Image MatchingRemote Sensing (test)
AUC@3px30.25
13
Pose EstimationMETU-VisTIR RGB-IR (test)
AUC@5°40.49
13
Pose EstimationAny-syn RGB-IR synthetic (test)
AUC @ 5 deg50.91
13
Pose EstimationAny-syn RGB-Depth synthetic (test)
AUC @ 5°14.05
13
Pose EstimationAny-syn RGB-Normal synthetic (test)
AUC @ 5°36.28
13
Pose EstimationAny-syn RGB-Event synthetic (test)
AUC @ 5°4.81
13
Showing 10 of 10 rows

Other info

Follow for update