3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images

TL;DR

This paper extends 3D Gaussian Splatting to large-scale aerial scene reconstruction by introducing data chunking, depth estimation, and multi-view consistency, achieving comparable or superior results to traditional methods.

Contribution

We propose Aerial Gaussian Splatting, a novel large-scale surface reconstruction method that adapts 3DGS for aerial images with new data handling and consistency techniques.

Findings

Achieves geometric accuracy comparable to conventional aerial MVS methods.

Outperforms state-of-the-art Gaussian Splatting methods in geometry and rendering quality.

Successfully reconstructs large-scale scenes from aerial multi-view stereo images.

Abstract

Recently, 3D Gaussian Splatting (3DGS) has demonstrated excellent ability in small-scale 3D surface reconstruction. However, extending 3DGS to large-scale scenes remains a significant challenge. To address this gap, we propose a novel 3DGS-based method for large-scale surface reconstruction using aerial multi-view stereo (MVS) images, named Aerial Gaussian Splatting (AGS). First, we introduce a data chunking method tailored for large-scale aerial images, making 3DGS feasible for surface reconstruction over extensive scenes. Second, we integrate the Ray-Gaussian Intersection method into 3DGS to obtain depth and normal information. Finally, we implement multi-view geometric consistency constraints to enhance the geometric consistency across different views. Our experiments on multiple datasets demonstrate, for the first time, the 3DGS-based method can match conventional aerial MVS methods on geometric accuracy in aerial large-scale surface reconstruction, and our method also beats state-of-the-art GS-based methods both on geometry and rendering quality.