SF-Recon: 无需简化轻量级建筑重建 via 3D 高斯点划法
SF-Recon: Simplification-Free Lightweight Building Reconstruction via 3D Gaussian Splatting
AI总结：
SF-Recon 通过 3D 高斯点划法直接重建轻量级建筑模型，无需后期简化，实现高效且结构忠实的建筑网格生成。
摘要：
轻量级建筑表面模型对于数字城市、导航和快速地理空间分析至关重要，然而传统多视图几何管线仍然笨重且质量敏感，因为它们依赖于密集重建、建模和随后的简化。本文提出 SF-Recon，一种从多视图图像中直接重建轻量级建筑表面的方法，无需后期网格简化。我们首先训练一个初始的 3D 高斯点划法 (3DGS) 字段以获得视图一致的表示。然后通过法向量梯度引导的高斯优化来提取建筑结构，该优化选择与屋顶和墙面边界对齐的原始体素，随后通过多视图边缘一致性修剪来增强结构锐度并抑制非结构化伪影，而无需外部监督。最后，多视图深度约束的德劳内三角化将结构化的高斯场转换为轻量级、结构忠实的建筑网格。基于所提出的 SF 数据集，实验结果表明，我们的 SF-Recon 可以直接从多视图图像中重建轻量级建筑模型，实现远少于面和顶点的同时保持计算效率。网站：https://lzh282140127-cell.github.io/SF-Recon-project/
英文摘要：
Lightweight building surface models are crucial for digital city, navigation, and fast geospatial analytics, yet conventional multi-view geometry pipelines remain cumbersome and quality-sensitive due to their reliance on dense reconstruction, meshing, and subsequent simplification. This work presents SF-Recon, a method that directly reconstructs lightweight building surfaces from multi-view images without post-hoc mesh simplification. We first train an initial 3D Gaussian Splatting (3DGS) field to obtain a view-consistent representation. Building structure is then distilled by a normal-gradient-guided Gaussian optimization that selects primitives aligned with roof and wall boundaries, followed by multi-view edge-consistency pruning to enhance structural sharpness and suppress non-structural artifacts without external supervision. Finally, a multi-view depth-constrained Delaunay triangulation converts the structured Gaussian field into a lightweight, structurally faithful building mesh. Based on a proposed SF dataset, the experimental results demonstrate that our SF-Recon can directly reconstruct lightweight building models from multi-view imagery, achieving substantially fewer faces and vertices while maintaining computational efficiency. Website:https://lzh282140127-cell.github.io/SF-Recon-project/
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。
