解决3D高斯泼溅SLAM的漂移问题，提升大场景定位精度
GLC-SLAM: Gaussian Splatting SLAM with Efficient Loop Closure
- 分块3D高斯子地图+全局到局部回环检测，抑制累积误差
- 关键帧按不确定性筛选，优化子地图更新效率
- 在多个数据集上优于或媲美顶尖稠密RGB-D SLAM系统
3D高斯泼溅（3DGS）因其在稠密同步定位与地图构建（SLAM）中的应用而受到广泛关注，可实现实时渲染与高保真建图。然而，现有基于3DGS的SLAM方法在大规模环境中常面临跟踪误差累积和地图漂移问题。为此，我们提出GLC-SLAM，一种集成相机位姿与场景模型全局优化的高斯泼溅SLAM系统。该方法采用帧到模型追踪，并通过全局到局部策略触发分层回环闭合以减少漂移。通过将场景划分为3D高斯子地图，实现大场景下回环修正后的高效地图更新。此外，采用不确定性最小化的关键帧选择策略，优先选取观测更多有价值3D高斯点的关键帧，以增强子地图优化效果。在多个数据集上的实验结果表明，GLC-SLAM在跟踪与建图性能上均优于或媲美当前最先进的稠密RGB-D SLAM系统。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has gained significant attention for its application in dense Simultaneous Localization and Mapping (SLAM), enabling real-time rendering and high-fidelity mapping. However, existing 3DGS-based SLAM methods often suffer from accumulated tracking errors and map drift, particularly in large-scale environments. To address these issues, we introduce GLC-SLAM, a Gaussian Splatting SLAM system that integrates global optimization of camera poses and scene models. Our approach employs frame-to-model tracking and triggers hierarchical loop closure using a global-to-local strategy to minimize drift accumulation. By dividing the scene into 3D Gaussian submaps, we facilitate efficient map updates following loop corrections in large scenes. Additionally, our uncertainty-minimized keyframe selection strategy prioritizes keyframes observing more valuable 3D Gaussians to enhance submap optimization. Experimental results on various datasets demonstrate that GLC-SLAM achieves superior or competitive tracking and mapping performance compared to state-of-the-art dense RGB-D SLAM systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。