3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images
This addresses the problem of large-scale 3D reconstruction for aerial imaging applications, representing an incremental advancement by adapting an existing method to a new scale.
The paper tackles the challenge of extending 3D Gaussian Splatting to large-scale surface reconstruction from aerial images, proposing Aerial Gaussian Splatting, which matches conventional aerial MVS methods in geometric accuracy and outperforms state-of-the-art GS-based methods in geometry and rendering quality.
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.