Guardado en:
Detalles Bibliográficos
Autores principales: Cheng, Luqi, Qi, Zhangshuo, Zhou, Zijie, Lu, Chao, Xiong, Guangming
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.01704
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918112495927296
author Cheng, Luqi
Qi, Zhangshuo
Zhou, Zijie
Lu, Chao
Xiong, Guangming
author_facet Cheng, Luqi
Qi, Zhangshuo
Zhou, Zijie
Lu, Chao
Xiong, Guangming
contents Maps play an important role in autonomous driving systems. The recently proposed 3D Gaussian Splatting (3D-GS) produces rendering-quality explicit scene reconstruction results, demonstrating the potential for map construction in autonomous driving scenarios. However, because of the time and computational costs involved in generating Gaussian scenes, how to update the map becomes a significant challenge. In this paper, we propose LT-Gaussian, a map update method for 3D-GS-based maps. LT-Gaussian consists of three main components: Multimodal Gaussian Splatting, Structural Change Detection Module, and Gaussian-Map Update Module. Firstly, the Gaussian map of the old scene is generated using our proposed Multimodal Gaussian Splatting. Subsequently, during the map update process, we compare the outdated Gaussian map with the current LiDAR data stream to identify structural changes. Finally, we perform targeted updates to the Gaussian-map to generate an up-to-date map. We establish a benchmark for map updating on the nuScenes dataset to quantitatively evaluate our method. The experimental results show that LT-Gaussian can effectively and efficiently update the Gaussian-map, handling common environmental changes in autonomous driving scenarios. Furthermore, by taking full advantage of information from both new and old scenes, LT-Gaussian is able to produce higher quality reconstruction results compared to map update strategies that reconstruct maps from scratch. Our open-source code is available at https://github.com/ChengLuqi/LT-gaussian.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01704
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving
Cheng, Luqi
Qi, Zhangshuo
Zhou, Zijie
Lu, Chao
Xiong, Guangming
Computer Vision and Pattern Recognition
Maps play an important role in autonomous driving systems. The recently proposed 3D Gaussian Splatting (3D-GS) produces rendering-quality explicit scene reconstruction results, demonstrating the potential for map construction in autonomous driving scenarios. However, because of the time and computational costs involved in generating Gaussian scenes, how to update the map becomes a significant challenge. In this paper, we propose LT-Gaussian, a map update method for 3D-GS-based maps. LT-Gaussian consists of three main components: Multimodal Gaussian Splatting, Structural Change Detection Module, and Gaussian-Map Update Module. Firstly, the Gaussian map of the old scene is generated using our proposed Multimodal Gaussian Splatting. Subsequently, during the map update process, we compare the outdated Gaussian map with the current LiDAR data stream to identify structural changes. Finally, we perform targeted updates to the Gaussian-map to generate an up-to-date map. We establish a benchmark for map updating on the nuScenes dataset to quantitatively evaluate our method. The experimental results show that LT-Gaussian can effectively and efficiently update the Gaussian-map, handling common environmental changes in autonomous driving scenarios. Furthermore, by taking full advantage of information from both new and old scenes, LT-Gaussian is able to produce higher quality reconstruction results compared to map update strategies that reconstruct maps from scratch. Our open-source code is available at https://github.com/ChengLuqi/LT-gaussian.
title LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.01704