紧凑的3D高斯散射用于密集视觉SLAM
Compact 3D Gaussian Splatting For Dense Visual SLAM
AI总结：
本文提出紧凑的3D高斯散射SLAM系统，通过滑动窗口遮罩策略和几何代码本压缩高斯参数，提升训练和渲染速度，保持高质量场景表示。
摘要：
近期研究表明，基于3D高斯的SLAM能够实现高质量重建、准确姿态估计和实时渲染。然而，这些方法依赖大量冗余的3D高斯椭球体，导致高内存和存储成本及缓慢的训练速度。为解决此限制，我们提出了一种紧凑的3D高斯散射SLAM系统，减少高斯椭球体的数量和参数规模。首先提出基于滑动窗口的遮罩策略以减少冗余椭球体。然后观察到大多数3D高斯椭球体的协方差矩阵（几何）极为相似，从而提出新的几何代码本来压缩3D高斯几何属性，即参数。通过具有重投影损失的全局捆绑调整方法实现鲁棒且准确的姿态估计。大量实验表明，我们的方法在保持最先进的（SOTA）场景表示质量的同时，实现了更快的训练和渲染速度。
英文摘要：
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.
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。
