Dual Covariance Gaussian Splatting SLAM: Decoupling Rendering and Registration for Robust Real-Time Tracking

2026-09-22

AI Summary

该研究通过提出双协方差参数化方法，解决了3D高斯点云SLAM中渲染与注册对单一协方差的不同需求冲突问题，提高了实时跟踪的鲁棒性和精度。

Abstract

ICP-based 3D Gaussian Splatting (3DGS) SLAM tracks in real time by registering incoming frames against map Gaussians, using each primitive's covariance for both rendering and registration. These two uses place conflicting demands on one covariance. The mapper shapes it to minimize photometric error, often flattening it against surfaces, while robust registration typically benefits from measurement uncertainty. We propose a dual-covariance parameterization. Each Gaussian keeps a single mean but holds two covariances: a rendering covariance optimized by the mapper, and a tracking covariance derived from an RGB-D sensor noise model. We further use the tracking covariances as Gaussian anchors for image corners, providing constraints in directions where depth geometry is weak. We evaluate on TUM RGB-D, ScanNet, Replica, and two outdoor sequences recorded with a RealSense D435i on wheeled and handheld platforms. We achieve robust tracking performance across multiple scenes and reduced odometry drift, while tracking at $\sim$ 60 FPS.

Problem

• Dual Covariance
• Gaussian Splatting
• SLAM
• Rendering
• Registration

Innovation

• Dual Covariance
• Gaussian Splatting
• SLAM
• Decoupling Rendering and Registration
• Robust Tracking