GigaSLAM：基于分层高斯泼溅的大规模单目SLAM
GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
AI总结：
本文提出GigaSLAM，一种结合分层稀疏体素高斯表示、度量深度跟踪与词袋回环的单目SLAM框架，实现千米级无边界室外场景的高精度定位与高保真渲染。
摘要：
仅使用单目RGB输入在大规模、无边界室外环境中进行跟踪与建图，对现有SLAM系统构成了重大挑战。传统的神经辐射场（NeRF）和3D高斯泼溅（3DGS）SLAM方法通常局限于小型、有边界的室内场景。为克服这些挑战，我们提出GigaSLAM，这是首个基于RGB NeRF/3DGS的千米级室外环境SLAM框架，并在KITTI、KITTI 360、4 Seasons和A2D2数据集上进行了验证。我们的方法采用分层稀疏体素地图表示，其中高斯由神经网络在多个细节层次上解码。该设计能够在广阔、无边界的场景中实现高效、可扩展的建图和高保真实视点渲染。在前端跟踪方面，GigaSLAM利用度量深度模型，并结合对极几何和PnP算法来精确估计位姿，同时引入基于词袋（Bag-of-Words）的回环检测机制，以在长轨迹上保持稳健对齐。因此，GigaSLAM在城市室外基准测试上提供了高精度跟踪和视觉真实的渲染，为大规模、长期场景建立了稳健的SLAM解决方案，并显著扩展了高斯泼溅SLAM系统在无边界室外环境中的适用性。GitHub：https://github.com/DengKaiCQ/GigaSLAM。
英文摘要：
Tracking and mapping in large-scale, unbounded outdoor environments using only monocular RGB input presents substantial challenges for existing SLAM systems. Traditional Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) SLAM methods are typically limited to small, bounded indoor settings. To overcome these challenges, we introduce GigaSLAM, the first RGB NeRF / 3DGS-based SLAM framework for kilometer-scale outdoor environments, as demonstrated on the KITTI, KITTI 360, 4 Seasons and A2D2 datasets. Our approach employs a hierarchical sparse voxel map representation, where Gaussians are decoded by neural networks at multiple levels of detail. This design enables efficient, scalable mapping and high-fidelity viewpoint rendering across expansive, unbounded scenes. For front-end tracking, GigaSLAM utilizes a metric depth model combined with epipolar geometry and PnP algorithms to accurately estimate poses, while incorporating a Bag-of-Words-based loop closure mechanism to maintain robust alignment over long trajectories. Consequently, GigaSLAM delivers high-precision tracking and visually faithful rendering on urban outdoor benchmarks, establishing a robust SLAM solution for large-scale, long-term scenarios, and significantly extending the applicability of Gaussian Splatting SLAM systems to unbounded outdoor environments. GitHub: https://github.com/DengKaiCQ/GigaSLAM.
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。
