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

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 19595 - 19604
• Main Authors: Yan, Chi, Qu, Delin, Xu, Dan, Zhao, Bin, Wang, Zhigang, Wang, Dong, Li, Xuelong
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: 3D Gaussian Splatting; Pipelines; Reliability engineering; Rendering (computer graphics); Runtime; Simultaneous localization and mapping; SLAM; Three-dimensional displays; Visualization
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52733.2024.01853

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 to reconstruct the whole scene rather than synthesize a static object in existing meth-ods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. Project page: https://gs-slam.github.io/.