NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Jingwei, Li, Mingrui, Sun, Lei, Tian, Aaron Xuxiang, Deng, Tianchen, Wang, Hongyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917996591579136
author Huang, Jingwei
Li, Mingrui
Sun, Lei
Tian, Aaron Xuxiang
Deng, Tianchen
Wang, Hongyu
author_facet Huang, Jingwei
Li, Mingrui
Sun, Lei
Tian, Aaron Xuxiang
Deng, Tianchen
Wang, Hongyu
contents SLAM systems based on Gaussian Splatting have garnered attention due to their capabilities for rapid real-time rendering and high-fidelity mapping. However, current Gaussian Splatting SLAM systems usually struggle with large scene representation and lack effective loop closure detection. To address these issues, we introduce NGM-SLAM, the first 3DGS based SLAM system that utilizes neural radiance field submaps for progressive scene expression, effectively integrating the strengths of neural radiance fields and 3D Gaussian Splatting. We utilize neural radiance field submaps as supervision and achieve high-quality scene expression and online loop closure adjustments through Gaussian rendering of fused submaps. Our results on multiple real-world scenes and large-scale scene datasets demonstrate that our method can achieve accurate hole filling and high-quality scene expression, supporting monocular, stereo, and RGB-D inputs, and achieving state-of-the-art scene reconstruction and tracking performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05702
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
Huang, Jingwei
Li, Mingrui
Sun, Lei
Tian, Aaron Xuxiang
Deng, Tianchen
Wang, Hongyu
Robotics
SLAM systems based on Gaussian Splatting have garnered attention due to their capabilities for rapid real-time rendering and high-fidelity mapping. However, current Gaussian Splatting SLAM systems usually struggle with large scene representation and lack effective loop closure detection. To address these issues, we introduce NGM-SLAM, the first 3DGS based SLAM system that utilizes neural radiance field submaps for progressive scene expression, effectively integrating the strengths of neural radiance fields and 3D Gaussian Splatting. We utilize neural radiance field submaps as supervision and achieve high-quality scene expression and online loop closure adjustments through Gaussian rendering of fused submaps. Our results on multiple real-world scenes and large-scale scene datasets demonstrate that our method can achieve accurate hole filling and high-quality scene expression, supporting monocular, stereo, and RGB-D inputs, and achieving state-of-the-art scene reconstruction and tracking performance.
title NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
topic Robotics
url https://arxiv.org/abs/2405.05702