LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving

TL;DR

LT-Gaussian introduces an efficient method for updating 3D Gaussian Splatting maps in autonomous driving, effectively detecting structural changes and maintaining high-quality scene reconstructions with less computational cost.

Contribution

The paper presents a novel map update approach for 3D-Gaussian Splatting that detects structural changes and updates maps efficiently, improving over previous reconstruction methods.

Findings

Effective map updating on nuScenes dataset

Handles environmental changes efficiently

Produces higher quality reconstructions than from-scratch methods

Abstract

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 Subsequently, during the map update process, we compare the outdated Gaussian map with the current LiDAR data stream to identify structural changes.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.