用边缘监督提升无人机建模中建筑轮廓的清晰度
SharpSplat: Edge-Regularized 3D Gaussian Splatting for High Fidelity Urban Building Reconstruction from UAV images
- 引入语义边缘正则化，让3D高斯点云自动对齐建筑边界
- 在校园、城区等多场景下，边缘清晰度显著提升
- 无需改动原模型结构，适合城市数字孪生应用
从无人机影像重建高保真三维建筑模型是构建大规模数字孪生的关键。然而，现有3D高斯点云（3DGS）方法在建筑立面重建上常难以捕捉锐利的几何过渡。为此，我们提出一种语义边缘正则化框架，通过SAM 3生成精确建筑掩码并提取重要建筑边缘，在训练中使渲染图像梯度与这些边缘对齐，促使高斯点云收敛为清晰的结构几何形态。在校园环境、密集城区及定制住宅数据集上的评估表明，该方法在不修改3DGS管道的前提下，显著提升了边缘保真度，且对不同建筑类型、屋顶结构和城市密度均表现出鲁棒性。
原文摘要 · Abstract (English)
Reconstructing high-fidelity 3D building models from UAV imagery is essential for large-scale digital twin development. However, existing 3D Gaussian Splatting (3DGS) techniques often struggle with building facades, failing to capture sharp geometric transitions. To address this, we propose a semantic edge regularization framework that supervises 3DGS to produce crisp architectural boundaries. Our method leverages SAM 3 to generate precise building masks, from which we extract architecturally significant edges. During training, we align rendered image gradients with these extracted edges, forcing the Gaussians to converge into sharp structural geometries. Evaluations across campus environments, dense urban centers, and custom residential datasets demonstrate significant improvements in edge fidelity without requiring architectural modifications to the 3DGS pipeline. Our approach proves robust across diverse building types, roof geometries, and urban densities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。