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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Chi, Qu, Delin, Xu, Dan, Zhao, Bin, Wang, Zhigang, Wang, Dong, Li, Xuelong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910401050968064
author Yan, Chi
Qu, Delin
Xu, Dan
Zhao, Bin
Wang, Zhigang
Wang, Dong
Li, Xuelong
author_facet Yan, Chi
Qu, Delin
Xu, Dan
Zhao, Bin
Wang, Zhigang
Wang, Dong
Li, Xuelong
contents In this paper, we introduce \textbf{GS-SLAM} that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization 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 previously observed areas. This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods. 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11700
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
Yan, Chi
Qu, Delin
Xu, Dan
Zhao, Bin
Wang, Zhigang
Wang, Dong
Li, Xuelong
Computer Vision and Pattern Recognition
In this paper, we introduce \textbf{GS-SLAM} that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization 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 previously observed areas. This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods. 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/.
title GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.11700