CM-Bench: A Comprehensive Cross-Modal Feature Matching Benchmark Bridging Visible and Infrared Images

TL;DR

This paper introduces CM-Bench, a comprehensive benchmark for cross-modal feature matching between visible and infrared images, evaluating various algorithms and proposing an adaptive preprocessing method to improve matching performance.

Contribution

The paper provides the first standardized benchmark for IR-VIS feature matching, categorizes existing methods, and introduces a new dataset with ground-truth for geo-localization tasks.

Findings

Evaluation of 30 feature matching algorithms across diverse datasets

Introduction of an adaptive preprocessing front-end for better matching

A new infrared-satellite dataset for geo-localization

Abstract

Infrared-visible (IR-VIS) feature matching plays an essential role in cross-modality visual localization, navigation and perception. Along with the rapid development of deep learning techniques, a number of representative image matching methods have been proposed. However, crossmodal feature matching is still a challenging task due to the significant appearance difference. A significant gap for cross-modal feature matching research lies in the absence of standardized benchmarks and metrics for evaluations. In this paper, we introduce a comprehensive cross-modal feature matching benchmark, CM-Bench, which encompasses 30 feature matching algorithms across diverse cross-modal datasets. Specifically, state-of-the-art traditional and deep learning-based methods are first summarized and categorized into sparse, semidense, and dense methods. These methods are evaluated by different tasks including homography estimation, relative pose estimation, and feature-matching-based geo-localization. In addition, we introduce a classification-network-based adaptive preprocessing front-end that automatically selects suitable enhancement strategies before matching. We also present a novel infrared-satellite cross-modal dataset with manually annotated ground-truth correspondences for practical geo-localization evaluation. The dataset and resource will be available at: https://github.com/SLZ98/CM-Bench.