Thermal odometry and dense mapping using learned odometry and Gaussian splatting

TL;DR

TOM-GS is a novel thermal SLAM system that combines learning-based odometry with Gaussian splatting for dense mapping, improving robustness and reconstruction quality in challenging conditions.

Contribution

It introduces the first Gaussian splatting-based SLAM tailored for thermal cameras, integrating learning-based odometry with dense thermal mapping.

Findings

Outperforms existing learning-based thermal odometry methods

Provides high-quality dense thermal maps

Demonstrates robustness across diverse datasets

Abstract

Thermal infrared sensors, with wavelengths longer than smoke particles, can capture imagery independent of darkness, dust, and smoke. This robustness has made them increasingly valuable for motion estimation and environmental perception in robotics, particularly in adverse conditions. Existing thermal odometry and mapping approaches, however, are predominantly geometric and often fail across diverse datasets while lacking the ability to produce dense maps. Motivated by the efficiency and high-quality reconstruction ability of recent Gaussian Splatting (GS) techniques, we propose TOM-GS, a thermal odometry and mapping method that integrates learning-based odometry with GS-based dense mapping. TOM-GS is among the first GS-based SLAM systems tailored for thermal cameras, featuring dedicated thermal image enhancement and monocular depth integration. Extensive experiments on motion estimation and novel-view rendering demonstrate that TOM-GS outperforms existing learning-based methods, confirming the benefits of learning-based pipelines for robust thermal odometry and dense reconstruction.