GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting

TL;DR

This paper presents U-Scene, a large-scale urban dataset with RGB and LiDAR data, and evaluates Gaussian Splatting for scene reconstruction, highlighting the importance of multi-modal data integration.

Contribution

Introduces U-Scene, a comprehensive large-scale dataset, and evaluates Gaussian Splatting for scene reconstruction, emphasizing multi-modal data benefits.

Findings

Gaussian Splatting performs well on large-scale scenes.

Multi-modal data improves reconstruction accuracy.

Significant differences observed between RGB and LiDAR-based reconstructions.

Abstract

We introduce a novel large-scale scene reconstruction benchmark using the newly developed 3D representation approach, Gaussian Splatting, on our expansive U-Scene dataset. U-Scene encompasses over one and a half square kilometres, featuring a comprehensive RGB dataset coupled with LiDAR ground truth. For data acquisition, we employed the Matrix 300 drone equipped with the high-accuracy Zenmuse L1 LiDAR, enabling precise rooftop data collection. This dataset, offers a unique blend of urban and academic environments for advanced spatial analysis convers more than 1.5 km$^2$. Our evaluation of U-Scene with Gaussian Splatting includes a detailed analysis across various novel viewpoints. We also juxtapose these results with those derived from our accurate point cloud dataset, highlighting significant differences that underscore the importance of combine multi-modal information