$S^3$LAM: Surfel Splatting SLAM for Geometrically Accurate Tracking and Mapping

TL;DR

$S^3$LAM introduces a surfel splatting SLAM system that uses 2D Gaussian surfels for efficient, high-quality geometry reconstruction and accurate tracking in real-time, outperforming existing methods.

Contribution

The paper presents a novel SLAM approach leveraging 2D surfel splatting for improved geometric accuracy and efficiency, with a new adaptive rendering strategy and direct Jacobian derivation.

Findings

Achieves state-of-the-art accuracy on synthetic and real datasets.

Demonstrates efficient real-time performance with improved mapping quality.

Validates the effectiveness of 2D surfel primitives over 3D Gaussian ellipsoids.

Abstract

We propose $S^3$LAM, a novel RGB-D SLAM system that leverages 2D surfel splatting to achieve highly accurate geometric representations for simultaneous tracking and mapping. Unlike existing 3DGS-based SLAM approaches that rely on 3D Gaussian ellipsoids, we utilize 2D Gaussian surfels as primitives for more efficient scene representation. By focusing on the surfaces of objects in the scene, this design enables $S^3$LAM to reconstruct high-quality geometry, benefiting both mapping and tracking. To address inherent SLAM challenges including real-time optimization under limited viewpoints, we introduce a novel adaptive surface rendering strategy that improves mapping accuracy while maintaining computational efficiency. We further derive camera pose Jacobians directly from 2D surfel splatting formulation, highlighting the importance of our geometrically accurate representation that improves tracking convergence. Extensive experiments on both synthetic and real-world datasets validate that $S^3$LAM achieves state-of-the-art performance. Code will be made publicly available.