GeoGS-SLAM：用于密集单目 SLAM 的仅几何高斯点云法
GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM
AI总结：
研究针对密集视觉 SLAM 问题，提出仅几何高斯点云法（GeoGS）及基于此的 GeoGS-SLAM 系统。该方法仅保留空间参数减少基元参数，专注几何重建，通过有效训练框架和地图更新策略，提升在线映射效率与几何重建质量。
摘要：
密集视觉 SLAM 是机器人领域的一个基本问题。3DGS 的最新进展已证明其在密集 SLAM 中的潜力。现有 3DGS 框架同时关注外观和几何建模。然而，场景几何对于 SLAM 通常比新视图合成更关键，因为诸如导航和避障等下游机器人任务主要依赖准确的空间几何而非逼真渲染。由此提出问题：3DGS 不进行场景外观建模来执行 3D 重建是否可行？基于此，提出仅几何高斯点云法（GeoGS）直接重建场景几何，并进一步提出 GeoGS-SLAM 密集视觉 SLAM 系统。GeoGS 仅保留空间参数，减少了每个基元参数的 80%以上。与现有方法相比，它仅专注于几何重建，减少了高斯基元数量，加速了几何收敛并增强了对光照变化的鲁棒性。还提出了一个有效的训练框架，通过单视图和多视图几何及光度监督来优化高斯基元，并通过局部平面驱动初始化加速几何收敛。此外，引入了一种用于回环闭合的地图更新策略，全局变换高斯地图以使其与校正后的姿态估计对齐，防止现有方法中因每个视点姿态校正不一致导致的地图撕裂。在合成和真实世界基准上的大量实验表明，该方法在在线映射效率和几何重建质量方面优于现有方法。
英文摘要：
Dense visual SLAM is a fundamental problem in robotics. Recent advances in 3DGS have demonstrated its potential for dense SLAM. Existing 3DGS frameworks focus on both appearance and geometry modeling. However, scene geometry is typically more critical for SLAM than novel view synthesis because downstream robotic tasks, such as navigation and obstacle avoidance, rely primarily on accurate spatial geometry rather than photorealistic rendering. This observation raises a natural question: Is it feasible for 3DGS to perform 3D reconstruction without scene appearance modeling? Motivated by this, we propose Geometry-only Gaussian Splatting (GeoGS), which directly reconstructs scene geometry, and further present GeoGS-SLAM, a dense visual SLAM system built upon this representation. Specifically, GeoGS retains only spatial parameters to reduce the number of per-primitive parameters by over 80%. In contrast to existing 3DGS methods, GeoGS focuses solely on geometric reconstruction, which significantly reduces the number of Gaussian primitives, accelerates geometric convergence, and enhances robustness to illumination variations. In addition, we present an effective training framework that optimizes the Gaussian primitives via single-view and multi-view geometric and photometric supervision, and speeds up geometry convergence with a local-plane driven initialization that better aligns primitives with local structures. Furthermore, we introduce a map update strategy for loop closure that globally transforms the Gaussian map to align it with the corrected pose estimates, thereby preventing map tearing caused by inconsistent per-viewpoint pose corrections in existing methods. Extensive experiments on synthetic and real-world benchmarks demonstrate that our method outperforms SOTA methods in terms of online mapping efficiency and geometric reconstruction quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
