用热成像做精准定位与稠密建图，支持黑暗烟雾环境
Thermal odometry and dense mapping using learned odometry and Gaussian splatting
- 融合学习型里程计与高斯点阵重建热成像
- 在多场景下实现优于现有方法的定位精度与视图生成
- 适合机器人在火灾等恶劣环境中进行感知
热红外传感器因波长超过烟尘粒子，可在黑暗、粉尘和烟雾中独立成像，使其在机器人运动估计与环境感知中愈发重要。然而，现有热成像里程计与建图方法多为几何主导，跨数据集表现差，且无法生成稠密地图。受近期高斯点阵（Gaussian Splatting, GS）技术高效与高质量重建能力启发，本文提出TOM-GS，一种将学习型里程计与GS稠密建图结合的热成像定位与建图方法。TOM-GS是首个专为热成像相机设计的基于GS的SLAM系统，包含专用热图像增强与单目深度融合模块。大量实验表明，该方法在运动估计与新视角渲染方面均优于现有学习型方法，验证了学习型流水线在鲁棒热成像里程计与稠密重建中的优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。