VarSplat: 一种具有不确定性的3D高斯点划法用于鲁棒的RGB-D SLAM
VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM
AI总结：
VarSplat通过显式学习每个点划的外观方差，提升RGB-D SLAM的鲁棒性和稳定性，实现更可靠的跟踪与建图。
摘要：
同时定位与建图（SLAM）使用3D高斯点划法（3DGS）可以实现快速、可微分的渲染和在多样化的现实场景中的高保真重建。然而，现有3DGS-SLAM方法隐式处理测量可靠性，导致姿态估计和全局对齐在低纹理区域、透明表面或复杂反射特性区域容易产生漂移。为此，我们引入VarSplat，一种具有不确定性的3DGS-SLAM系统，该系统显式学习每个点划的外观方差。通过使用总方差定律与alpha混合，我们然后通过高效、单次遍历的光栅化技术渲染可微分的每像素不确定性图。该图指导跟踪、子图注册和环检测，以聚焦于可靠的区域，并有助于更稳定的优化。在Replica（合成）和TUM-RGBD、ScanNet和ScanNet++（现实世界）上的实验结果表明，VarSplat提高了鲁棒性，并在密集RGB-D SLAM中实现了与现有研究相比相媲美或更优的跟踪、建图和新视图合成渲染性能。
英文摘要：
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.
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。
