Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery

TL;DR

This paper presents a novel method for 3D urban scene reconstruction using Gaussian Splatting and Google Earth imagery, achieving superior view synthesis and detailed 3D geometry compared to previous neural radiance field approaches.

Contribution

It introduces a 3D Gaussian Splatting model for large-scale urban scenes that surpasses existing view synthesis methods and accurately reconstructs scene geometry from satellite imagery.

Findings

Outperforms neural radiance fields in view synthesis quality

Accurately reconstructs 3D geometry from satellite images

Demonstrates effective large-scale urban scene modeling

Abstract

3D urban scene reconstruction and modelling is a crucial research area in remote sensing with numerous applications in academia, commerce, industry, and administration. Recent advancements in view synthesis models have facilitated photorealistic 3D reconstruction solely from 2D images. Leveraging Google Earth imagery, we construct a 3D Gaussian Splatting model of the Waterloo region centered on the University of Waterloo and are able to achieve view-synthesis results far exceeding previous 3D view-synthesis results based on neural radiance fields which we demonstrate in our benchmark. Additionally, we retrieved the 3D geometry of the scene using the 3D point cloud extracted from the 3D Gaussian Splatting model which we benchmarked against our Multi- View-Stereo dense reconstruction of the scene, thereby reconstructing both the 3D geometry and photorealistic lighting of the large-scale urban scene through 3D Gaussian Splatting