Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian ellipsoids, leading to high memory and storage costs, and slow training speed. To address the limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then we observe that the covariance matrix (geometry) of most 3D Gaussian ellipsoids are extremely similar, which motivates a novel geometry codebook to compress 3D Gaussian geometric attributes, i.e., the parameters. Robust and accurate pose estimation is achieved by a global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training and rendering speed while maintaining the state-of-the-art (SOTA) quality of the scene representation.

翻译：近期研究表明，基于3D高斯的SLAM能够实现高质量场景重建、精确位姿估计与实时渲染。然而，现有方法建立在海量冗余的3D高斯椭球体基础上，导致高昂的内存与存储开销以及缓慢的训练速度。为突破此限制，我们提出一种紧凑型3D高斯溅射SLAM系统，通过减少高斯椭球体的数量与参数量实现高效表达。我们首先提出基于滑动窗口的掩码策略以消除冗余椭球体，进而发现多数3D高斯椭球体的协方差矩阵（几何属性）具有高度相似性，据此设计新型几何码本以压缩3D高斯的几何属性参数。通过结合重投影损失的全局光束法平差方法，实现了鲁棒且精确的位姿估计。大量实验表明，本方法在保持场景表征质量达到最先进水平的同时，显著提升了训练与渲染速度。