Large-Scale Gaussian Splatting SLAM

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xin, Zhe, Wu, Chenyang, Huang, Penghui, Zhang, Yanyong, Mao, Yinian, Huang, Guoquan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910944984039424
author Xin, Zhe
Wu, Chenyang
Huang, Penghui
Zhang, Yanyong
Mao, Yinian
Huang, Guoquan
author_facet Xin, Zhe
Wu, Chenyang
Huang, Penghui
Zhang, Yanyong
Mao, Yinian
Huang, Guoquan
contents The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor environments. The robustness of reconstruction in large-scale outdoor scenarios remains unexplored. This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM. The proposed LSG-SLAM employs a multi-modality strategy to estimate prior poses under large view changes. In tracking, we introduce feature-alignment warping constraints to alleviate the adverse effects of appearance similarity in rendering losses. For the scalability of large-scale scenarios, we introduce continuous Gaussian Splatting submaps to tackle unbounded scenes with limited memory. Loops are detected between GS submaps by place recognition and the relative pose between looped keyframes is optimized utilizing rendering and feature warping losses. After the global optimization of camera poses and Gaussian points, a structure refinement module enhances the reconstruction quality. With extensive evaluations on the EuRoc and KITTI datasets, LSG-SLAM achieves superior performance over existing Neural, 3DGS-based, and even traditional approaches. Project page: https://lsg-slam.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large-Scale Gaussian Splatting SLAM
Xin, Zhe
Wu, Chenyang
Huang, Penghui
Zhang, Yanyong
Mao, Yinian
Huang, Guoquan
Computer Vision and Pattern Recognition
Robotics
The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor environments. The robustness of reconstruction in large-scale outdoor scenarios remains unexplored. This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM. The proposed LSG-SLAM employs a multi-modality strategy to estimate prior poses under large view changes. In tracking, we introduce feature-alignment warping constraints to alleviate the adverse effects of appearance similarity in rendering losses. For the scalability of large-scale scenarios, we introduce continuous Gaussian Splatting submaps to tackle unbounded scenes with limited memory. Loops are detected between GS submaps by place recognition and the relative pose between looped keyframes is optimized utilizing rendering and feature warping losses. After the global optimization of camera poses and Gaussian points, a structure refinement module enhances the reconstruction quality. With extensive evaluations on the EuRoc and KITTI datasets, LSG-SLAM achieves superior performance over existing Neural, 3DGS-based, and even traditional approaches. Project page: https://lsg-slam.github.io.
title Large-Scale Gaussian Splatting SLAM
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2505.09915