G2S-ICP SLAM: Geometry-aware Gaussian Splatting ICP SLAM

TL;DR

G2S-ICP SLAM introduces a geometry-aware Gaussian Splatting approach for real-time, high-fidelity RGB-D SLAM, improving pose accuracy and scene reconstruction by modeling local surfaces with surface-aligned Gaussians.

Contribution

The paper proposes a novel geometry-aware Gaussian Splatting representation integrated into ICP SLAM, enhancing depth consistency and registration accuracy in real-time.

Findings

Outperforms prior SLAM systems in localization accuracy.

Achieves high-quality 3D reconstruction and rendering.

Operates in real-time with high fidelity.

Abstract

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.