发表机构
HERON - Hellenic Robotics Center of Excellence, Athena Research Center; Institute of Robotics, Athena Research Center; National Technical University of Athens（希腊机器人卓越中心 - 阿西娜研究中心; 阿西娜研究中心机器人研究所; 雅典国立技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有高斯点云SLAM系统的局限，GLAM-SLAM提出实时解耦系统，用基于特征的前端跟踪，结构化网格映射，引入流致密化和场景划分策略，在多数据集上评估，性能优于同类，提升15%，且保持实时与可扩展性，代码开源。
AI 中文摘要
现有的基于高斯点云的单目同时定位与映射（SLAM）系统，要么适用于短序列，要么非实时，要么GPU内存需求过高，限制了其在实际长距离场景中的应用。为此，我们提出了GLAM-SLAM，一种为大规模户外场景设计的实时、解耦的高斯点云SLAM系统。我们使用强大的基于特征的SLAM前端确保轻量级跟踪，映射时采用结构化稀疏锚点网格表示以确保可扩展操作并保持长期序列的场景连贯性。为满足3D高斯点云的密集初始化要求，引入基于几何的流致密化锚定策略。通过将映射视为多场景问题，提出场景划分策略。在多个数据集上评估，结果表明比第二优性能提升15%，保持实时性和可扩展性，代码公开。
英文摘要
Existing Gaussian-splatting-based monocular Simultaneous Localization and Mapping (SLAM) systems are either tailored to short sequences, are not real-time, or suffer from prohibitive GPU memory requirements, limiting their applicability in realistic, long-horizon scenarios. To address this, we present GLAM-SLAM, a real-time, decoupled Gaussian-splatting SLAM system designed for large-scale outdoor scenes. We ensure lightweight tracking using a robust, feature-based SLAM frontend, while for mapping, we adopt a structured, sparse anchor grid representation that ensures scalable operation and maintains scene coherence across long-term sequences. To satisfy the dense initialization requirements of 3D Gaussian Splatting (3DGS), we introduce a geometry-based flow-densification anchoring strategy using epipolar constraints. Furthermore, by treating mapping as a multi-scene problem, we propose a scene-partitioning strategy that introduces a strong spatial inductive bias via MLP initializations to generate localized Gaussians. We evaluate our system on the challenging, long-sequence KITTI Odometry, Oxford RobotCar, and M'alaga datasets. Extensive ablations and comparisons demonstrate a 15% improvement in reconstruction quality over the second-best performer, while maintaining real-time performance and the ability to scale to longer sequences. Code is publicly available for the benefit of the community.
CommentsAccepted to IROS 2026. Project page: https://glamslam.github.io/ Code: https://github.com/pmermigkas/GLAM-SLAM/
