VarSplat：面向鲁棒 RGB-D SLAM 的不确定性感知三维高斯泼溅
VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM
把每个高斯球的外观方差作为可学习量，并用全方差定律配合 alpha 合成，在单次光栅化中渲染出逐像素不确定性图；这张图可直接用于跟踪、子图配准与回环检测的加权，是做 3DGS-SLAM 或任何需要衡量重建置信度的人可以复用的手段。
原文依据 we introduce VarSplat, an uncertainty-aware 3DGS-SLAM system that explicitly learns per-splat appearance variance
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于三维高斯泼溅（3DGS）的同时定位与建图（SLAM）能够在多样化的真实场景中实现快速的可微渲染与高保真重建。然而，现有 3DGS-SLAM 方法对测量可靠性采取隐式处理，使得姿态估计与全局对齐在低纹理区域、透明表面或反射特性复杂的区域容易受到漂移的影响。为此，我们提出 VarSplat，一个不确定性感知的 3DGS-SLAM 系统，它显式地学习每个高斯球的外观方差。借助全方差定律与 alpha 合成，我们随后通过高效的单次光栅化渲染出可微的逐像素不确定性图。该图引导跟踪、子图配准与回环检测聚焦于可靠区域，并有助于更稳定的优化。在 Replica（合成）以及 TUM-RGBD、ScanNet 和 ScanNet++（真实世界）上的实验结果表明，与现有的稠密 RGB-D SLAM 研究相比，VarSplat 提升了鲁棒性，并在跟踪、建图与新视角合成渲染方面取得了有竞争力或更优的表现。
英文原文摘要 1130 字符
Simultaneous Localization and Mapping (SLAM) with 3D Gaussian Splatting (3DGS) enables fast, differentiable rendering and high-fidelity reconstruction across diverse real-world scenes. However, existing 3DGS-SLAM approaches handle measurement reliability implicitly, making pose estimation and global alignment susceptible to drift in low-texture regions, transparent surfaces, or areas with complex reflectance properties. To this end, we introduce VarSplat, an uncertainty-aware 3DGS-SLAM system that explicitly learns per-splat appearance variance. By using the law of total variance with alpha compositing, we then render differentiable per-pixel uncertainty map via efficient, single-pass rasterization. This map guides tracking, submap registration, and loop detection toward focusing on reliable regions and contributes to more stable optimization. Experimental results on Replica (synthetic) and TUM-RGBD, ScanNet, and ScanNet++ (real-world) show that VarSplat improves robustness and achieves competitive or superior tracking, mapping, and novel view synthesis rendering compared to existing studies for dense RGB-D SLAM.