MGS-SLAM: Dense RGB-D SLAM via Multi-level Gaussian Splatting
Loading...
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Simultaneous localization and mapping (SLAM) are key technologies for scene perception, localization, and map construction. 3D Gaussian Splatting (3DGS), as a powerful method for geometric and appearance representation, has brought higher performance to SLAM systems. However, the existing methods based on 3D Gaussian representation use the single level of 3D Gaussian for the entire scene, resulting in their inability to effectively capture the geometric shapes and texture details of all objects in the scene. In this work, we propose a monocular dense RGB-D SLAM system that integrates multi-level features, which is achieved by using different levels of Gaussians to separately reconstruct geometric shapes and texture details. Specifically, through the Fourier transform, we capture the geometric shapes (low frequency) and texture details (high frequency) of the scene in the frequency domain, serving as the initial conditions for the Gaussian distribution. Additionally, to address the issue of different rendering outcomes (such as specular reflections) for the same 3D Gaussian under different viewpoints, we have integrated local adaptation Gaussian and local optimization techniques to compensate the discrepancies introduced by the 3D Gaussian across different viewpoints. Extensive quantitative and qualitative results demonstrate that our method outperforms the state-of-the-art methods.
Description
CCS Concepts: Computing methodologies → Reconstruction; Tracking
@inproceedings{10.2312:pg.20241274,
booktitle = {Pacific Graphics Conference Papers and Posters},
editor = {Chen, Renjie and Ritschel, Tobias and Whiting, Emily},
title = {{MGS-SLAM: Dense RGB-D SLAM via Multi-level Gaussian Splatting}},
author = {Wang, Xu and Liu, Ying and Chen, Xiaojun and Wu, Jialin and Zhang, Xiaohao and Li, Ruihui},
year = {2024},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-250-9},
DOI = {10.2312/pg.20241274}
}