Thegra: Graph-based SLAM for Thermal Imagery

TL;DR

This paper introduces a graph-based SLAM system for thermal imagery that uses learned features and a confidence-weighted factor graph, enabling robust localization in challenging environments without thermal-specific training.

Contribution

The work presents a novel thermal SLAM system leveraging general-purpose learned features and confidence integration, adapting existing detectors for thermal data without dataset-specific training.

Findings

Achieves reliable thermal SLAM performance on public datasets.

Does not require thermal-specific training or fine-tuning.

Effectively handles low-texture, noisy thermal images.

Abstract

Thermal imaging provides a practical sensing modality for visual SLAM in visually degraded environments such as low illumination, smoke, or adverse weather. However, thermal imagery often exhibits low texture, low contrast, and high noise, complicating feature-based SLAM. In this work, we propose a sparse monocular graph-based SLAM system for thermal imagery that leverages general-purpose learned features -- the SuperPoint detector and LightGlue matcher, trained on large-scale visible-spectrum data to improve cross-domain generalization. To adapt these components to thermal data, we introduce a preprocessing pipeline to enhance input suitability and modify core SLAM modules to handle sparse and outlier-prone feature matches. We further incorporate keypoint confidence scores from SuperPoint into a confidence-weighted factor graph to improve estimation robustness. Evaluations on public thermal datasets demonstrate that the proposed system achieves reliable performance without requiring dataset-specific training or fine-tuning a desired feature detector, given the scarcity of quality thermal data. Code will be made available upon publication.