Salvato in:
Dettagli Bibliografici
Autori principali: Lan, Tian, Lin, Qinwei, Wang, Haoqian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.13748
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916257361559552
author Lan, Tian
Lin, Qinwei
Wang, Haoqian
author_facet Lan, Tian
Lin, Qinwei
Wang, Haoqian
contents Recently,3DGaussianSplattinghasshowngreatpotentialin visual Simultaneous Localization And Mapping (SLAM). Existing methods have achieved encouraging results on RGB-D SLAM, but studies of the monocular case are still scarce. Moreover, they also fail to correct drift errors due to the lack of loop closure and global optimization. In this paper, we present MG-SLAM, a monocular Gaussian SLAM with a language-extended loop closure module capable of performing drift-corrected tracking and high-fidelity reconstruction while achieving a high-level understanding of the environment. Our key idea is to represent the global map as 3D Gaussian and use it to guide the estimation of the scene geometry, thus mitigating the efforts of missing depth information. Further, an additional language-extended loop closure module which is based on CLIP feature is designed to continually perform global optimization to correct drift errors accumulated as the system runs. Our system shows promising results on multiple challenging datasets in both tracking and mapping and even surpasses some existing RGB-D methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13748
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Monocular Gaussian SLAM with Language Extended Loop Closure
Lan, Tian
Lin, Qinwei
Wang, Haoqian
Computer Vision and Pattern Recognition
Recently,3DGaussianSplattinghasshowngreatpotentialin visual Simultaneous Localization And Mapping (SLAM). Existing methods have achieved encouraging results on RGB-D SLAM, but studies of the monocular case are still scarce. Moreover, they also fail to correct drift errors due to the lack of loop closure and global optimization. In this paper, we present MG-SLAM, a monocular Gaussian SLAM with a language-extended loop closure module capable of performing drift-corrected tracking and high-fidelity reconstruction while achieving a high-level understanding of the environment. Our key idea is to represent the global map as 3D Gaussian and use it to guide the estimation of the scene geometry, thus mitigating the efforts of missing depth information. Further, an additional language-extended loop closure module which is based on CLIP feature is designed to continually perform global optimization to correct drift errors accumulated as the system runs. Our system shows promising results on multiple challenging datasets in both tracking and mapping and even surpasses some existing RGB-D methods.
title Monocular Gaussian SLAM with Language Extended Loop Closure
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.13748