发表机构
School of Automation Science and Electrical Engineering, Beihang University; Hangzhou Innovation Institute, Beihang University; School of Mechanical Engineering, Zhejiang Sci-Tech University（北京航空航天大学自动化科学与电气工程学院; 北京航空航天大学杭州创新研究院; 浙江理工大学机械工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LightSplat提出混合表示RGB-D SLAM框架，结合局部稀疏特征跟踪与双线程高斯子地图构建，通过特征加速3DGS配准实现回环闭合，达到接近最先进的重建质量并保持8 FPS实时性能。
AI 中文摘要
基于3D高斯泼溅（3DGS）的SLAM系统近期在稠密3D场景表示的重建精度方面展现出令人期待的性能。然而，当前的3DGS系统由于在运行性能和地图适应性方面的严重限制，难以满足实际部署的严格要求。为此，我们提出了LightSplat，一种混合表示的RGB-D SLAM框架。它协同利用局部稀疏特征实现鲁棒且快速的跟踪，并通过双线程后端逐步构建稠密的高斯子地图。关键的是，我们通过特征加速的3DGS配准实现在线回环闭合，并通过位姿图优化来细化整体地图一致性。最终，LightSplat实现了高保真高斯地图的在线重建。在多个数据集和真实机器人平台上的大量实验表明，我们的方法达到了接近最先进的重建质量，并能够适应实际的相机运动，保持平均8帧每秒的帧率。总体而言，LightSplat为在真实环境中部署高保真3DGS提供了高效且鲁棒的基础。
英文摘要
SLAM systems based on 3D Gaussian Splatting (3DGS) have recently demonstrated promising reconstruction accuracy for dense 3D scene representations. However, current 3DGS systems struggle to meet the strict demands of real-world deployments due to severe limitations in operational performance and map adaptability. To this end, we propose LightSplat, a hybrid-representation RGB-D SLAM framework. It synergizes local sparse features for robust and fast tracking with a dual-thread backend that progressively constructs dense Gaussian submaps. Crucially, we enable online loop closure through feature-accelerated 3DGS registration, refining overall map consistency through pose graph optimization. Ultimately, LightSplat achieves the online reconstruction of high-fidelity Gaussian map. Extensive experiments on multiple datasets and real-world robotic platform demonstrate that our method achieves near state-of-the-art reconstruction quality and the capability to accommodate practical camera motions, maintaining an average framerate of 8 FPS. Overall, LightSplat provides an efficient and robust foundation for deploying high-fidelity 3DGS in real-world environments.
CommentsAccepted to 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
