GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition

GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition

|Authors: Panagiotis Mermigkas, Argyris Manetas, Petros Maragos

|Venue: arXiv preprint | Year: 2026

|arXiv: 2607.21416v1

Abstract

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.

Key Contributions

• Existing Gaussian-splatting-based monocular Simultaneous Localization and Mapping (SLAM) systems …
• To address this, we present GLAM-SLAM, a real-time, decoupled Gaussian-splatting SLAM system desi…
• We ensure lightweight tracking using a robust, feature-based SLAM frontend, while for mapping, we…
• To satisfy the dense initialization requirements of 3D Gaussian Splatting (3DGS), we introduce a …
• Furthermore, by treating mapping as a multi-scene problem, we propose a scene-partitioning strate…

Topics

• planning
• benchmark

Code & Data

• GitHub repository: https://github.com/pmermigkas/GLAM-SLAM

BibTeX

@article{Mermigkas2026_260721416v1,
  title     = {GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition},
  author    = {Panagiotis Mermigkas and Argyris Manetas and Petros Maragos},
  year      = {2026},
  eprint    = {2607.21416v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2607.21416v1}
}