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，基于三维高斯的SLAM技术能够实现高质量重建、精确位姿估计以及场景的实时渲染。然而，这些方法依赖于大量冗余的三维高斯椭球体，导致内存与存储成本高昂，且训练速度缓慢。针对这一局限性，我们提出了一种紧凑型三维高斯溅射SLAM系统，旨在减少高斯椭球体的数量与参数量。首先，我们提出了一种基于滑动窗口的掩码策略以减少冗余椭球体。随后，我们观察到大多数三维高斯椭球体的协方差矩阵（几何属性）具有极高相似性，这促使我们设计了一种新颖的几何编码本，用于压缩三维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示达到最新技术（SOTA）质量的同时，实现了更快的训练与渲染速度。