Thermal odometry and dense mapping using learned odometry and Gaussian splatting

2026-02-07

AI Summary

This work proposes the first end-to-end SLAM framework that integrates a learning-based thermal infrared visual odometry with Gaussian Splatting to address the limitations of existing geometric methods, which suffer from poor generalization and an inability to produce dense reconstructions. By jointly optimizing thermal image enhancement and monocular depth estimation, the method achieves robust pose estimation and high-quality dense mapping. Notably, it is the first to incorporate Gaussian Splatting into thermal infrared SLAM, outperforming current learning-based approaches in both pose accuracy and novel view synthesis. The framework significantly enhances system robustness and reconstruction fidelity in challenging environmental conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Remote Sensing / Geospatial AI
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• thermal odometry
• dense mapping
• thermal infrared sensors
• SLAM
• Gaussian Splatting

Innovation

• Thermal SLAM
• Gaussian Splatting
• Learning-based Odometry
• Dense Mapping
• Thermal Infrared Imaging