{"ID":5346699,"CreatedAt":"2026-06-30T04:09:55.830587294Z","UpdatedAt":"2026-07-02T15:01:14.507804213Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30436","arxiv_id":"2606.30436","title":"Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes","abstract":"Scaling monocular 3D Gaussian Splatting (3DGS) SLAM to kilometer-level outdoor environments poses two tightly coupled challenges: fragile long-term pose tracking and excessive memory overhead during large-scale mapping. In this paper, we propose KiloGS-SLAM, a highly efficient and robust monocular 3DGS-SLAM system that jointly addresses both bottlenecks. Since high-fidelity scene reconstruction fundamentally relies on drift-free camera poses, we first introduce a motion-adaptive hybrid tracking module. This module features a condition-triggered three-tier solving pipeline. It dynamically switches between Essential matrix and PnP models to handle geometric degeneracies. An on-demand foundation model can also be activated to rescue the trajectory from catastrophic drift. To ensure the system can sustain these long trajectories without memory exhaustion, we subsequently design a lifecycle-managed Gaussian mapping strategy. By integrating probabilistic initialization with chunk-based multi-view densification and pruning, this full-pipeline optimization effectively reduces primitive redundancy while preserving high-frequency details. Together, the robust tracking guarantees the geometric foundation required for accurate mapping, while the memory-efficient lifecycle-managed mapping enables large-scale operation. Extensive experiments across three challenging outdoor datasets demonstrate that our approach achieves state-of-the-art tracking accuracy and rendering quality, successfully scaling to sequences of over 10,000 frames on a single GPU.","short_abstract":"Scaling monocular 3D Gaussian Splatting (3DGS) SLAM to kilometer-level outdoor environments poses two tightly coupled challenges: fragile long-term pose tracking and excessive memory overhead during large-scale mapping. In this paper, we propose KiloGS-SLAM, a highly efficient and robust monocular 3DGS-SLAM system that...","url_abs":"https://arxiv.org/abs/2606.30436","url_pdf":"https://arxiv.org/pdf/2606.30436v1","authors":"[\"Sicheng Yu\",\"Dongxu Shen\",\"Beizhen Zhao\",\"Guanzhi Ding\",\"Hao Wang\"]","published":"2026-06-29T15:12:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}