基于3D Gaussian Splatting的航拍图像大规模表面重建
3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images
AI总结：
提出Aerial Gaussian Splatting (AGS)方法，通过数据分块、Ray-Gaussian Intersection集成及多视图几何一致性约束，实现航拍图像大规模表面重建，几何精度媲美传统MVS方法且渲染质量更优。
摘要：
最近，3D Gaussian Splatting (3DGS) 在小规模3D表面重建中展现出卓越能力。然而，将3DGS扩展到大规模场景仍是一个重大挑战。为填补这一空白，我们提出了一种基于3DGS的新方法，利用航拍多视图立体 (MVS) 图像进行大规模表面重建，命名为 Aerial Gaussian Splatting (AGS)。首先，我们引入一种针对大规模航拍图像的数据分块方法，使3DGS能够用于广阔场景的表面重建。其次，我们将 Ray-Gaussian Intersection 方法集成到3DGS中，以获取深度和法线信息。最后，我们实施多视图几何一致性约束，以增强不同视图间的几何一致性。我们在多个数据集上的实验首次表明，基于3DGS的方法在航拍大规模表面重建的几何精度上能媲美传统航拍MVS方法，并且我们的方法在几何和渲染质量上均超越了最先进的基于GS的方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
