Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery
This work addresses the problem of accurate and photorealistic 3D modeling for urban areas, which is important for remote sensing applications in academia, commerce, industry, and administration.
The paper tackled 3D urban scene reconstruction by using Gaussian Splatting with Google Earth imagery, achieving view-synthesis results that far exceed previous neural radiance field-based methods and reconstructing both 3D geometry and photorealistic lighting for a large-scale urban scene.
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