G2S-ICP SLAM：几何感知高斯泼溅 ICP SLAM
G2S-ICP SLAM: Geometry-aware Gaussian Splatting ICP SLAM
AI总结：
提出 G2S-ICP SLAM，用切平面约束的表面对齐二维高斯圆盘和各向异性 Generalized ICP 实现实时 RGB-D 跟踪与高保真重建。
摘要：
本文提出一种新颖的几何感知 RGB-D 高斯泼溅 SLAM 系统，名为 G2S-ICP SLAM。所提方法通过使用受局部切平面约束的高斯分布表示每个场景元素，实时执行高保真三维重建和鲁棒的相机位姿跟踪。这有效地将局部表面建模为与底层几何对齐的二维高斯圆盘；与传统的基于三维椭球、具有各向同性不确定性的表示相比，可在多个视点间获得更一致的深度解释。为将该表示集成到 SLAM 流程中，我们在不改变底层配准公式的情况下，通过引入各向异性协方差先验，将表面对齐的高斯圆盘嵌入 Generalized ICP 框架。此外，我们提出一种几何感知损失，用于监督光度、深度和法向一致性。我们的系统实现了实时运行，同时保持视觉和几何保真度。在 Replica 和 TUM-RGBD 数据集上的大量实验表明，G2S-ICP SLAM 在定位精度、重建完整性方面优于以往 SLAM 系统，同时保持了渲染质量。
英文摘要：
In this paper, we present a novel geometry-aware RGB-D Gaussian Splatting SLAM system, named G2S-ICP SLAM. The proposed method performs high-fidelity 3D reconstruction and robust camera pose tracking in real-time by representing each scene element using a Gaussian distribution constrained to the local tangent plane. This effectively models the local surface as a 2D Gaussian disk aligned with the underlying geometry, leading to more consistent depth interpretation across multiple viewpoints compared to conventional 3D ellipsoid-based representations with isotropic uncertainty. To integrate this representation into the SLAM pipeline, we embed the surface-aligned Gaussian disks into a Generalized ICP framework by introducing anisotropic covariance prior without altering the underlying registration formulation. Furthermore we propose a geometry-aware loss that supervises photometric, depth, and normal consistency. Our system achieves real-time operation while preserving both visual and geometric fidelity. Extensive experiments on the Replica and TUM-RGBD datasets demonstrate that G2S-ICP SLAM outperforms prior SLAM systems in terms of localization accuracy, reconstruction completeness, while maintaining the rendering quality.
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。
