articleJun 16, 2024Closed access

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

ShangHai JiAi Genetics & IVF Institute · Shanghai Artificial Intelligence Laboratory · +1 more institution

Indexed incrossref

Abstract

In this paper, we introduce GS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better bal-ance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting ren-dering pipeline that offers significant speedup to map opti-mization and RGB-D rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussians in order to efficiently reconstruct new observed scene geometry and improve the mapping of pre-viously observed areas. This strategy is essential to ex-tend 3D Gaussian representation…

No related works found for this paper.

Funding