GS4Buildings：用于3D建筑重建的先验引导高斯泼溅
GS4Buildings: Prior-Guided Gaussian Splatting for 3D Building Reconstruction
AI总结：
提出GS4Buildings，一种先验引导的2D高斯泼溅方法，通过利用LoD2语义3D建筑模型初始化高斯并引入先验深度和法线图优化，显著提升了大规模城市场景中建筑重建的完整性、几何精度和效率。
摘要：
Gaussian Splatting (GS) 的最新进展证明了其在照片级真实感渲染和3D重建中的有效性。其中，2D Gaussian Splatting (2DGS) 因其扁平化的高斯表示和集成的法线正则化，特别适合表面重建。然而，在频繁遮挡的大规模复杂城市场景中，其性能通常会下降，导致建筑重建不完整。我们提出了 GS4Buildings，一种新颖的先验引导 Gaussian Splatting 方法，利用无处不在的语义3D建筑模型来实现稳健且可扩展的建筑表面重建。GS4Buildings 不依赖传统的 Structure-from-Motion (SfM) 流程，而是直接从低层级的 Level of Detail (LoD)2 语义3D建筑模型初始化高斯。此外，我们从平面建筑几何中生成先验深度和法线图，并将其纳入优化过程，为表面一致性和结构准确性提供强大的几何引导。我们还引入了一种可选的聚焦建筑模式，将重建限制在建筑区域，实现了 Gaussian primitives 71.8%的减少，从而实现更高效紧凑的表示。在城市数据集上的实验表明，GS4Buildings 将重建完整性提高了20.5%，几何精度提高了32.8%。这些结果突显了语义建筑模型整合的潜力，推动基于GS的重建向智慧城市和数字孪生等现实世界城市应用迈进。
英文摘要：
Recent advances in Gaussian Splatting (GS) have demonstrated its effectiveness in photo-realistic rendering and 3D reconstruction. Among these, 2D Gaussian Splatting (2DGS) is particularly suitable for surface reconstruction due to its flattened Gaussian representation and integrated normal regularization. However, its performance often degrades in large-scale and complex urban scenes with frequent occlusions, leading to incomplete building reconstructions. We propose GS4Buildings, a novel prior-guided Gaussian Splatting method leveraging the ubiquity of semantic 3D building models for robust and scalable building surface reconstruction. Instead of relying on traditional Structure-from-Motion (SfM) pipelines, GS4Buildings initializes Gaussians directly from low-level Level of Detail (LoD)2 semantic 3D building models. Moreover, we generate prior depth and normal maps from the planar building geometry and incorporate them into the optimization process, providing strong geometric guidance for surface consistency and structural accuracy. We also introduce an optional building-focused mode that limits reconstruction to building regions, achieving a 71.8% reduction in Gaussian primitives and enabling a more efficient and compact representation. Experiments on urban datasets demonstrate that GS4Buildings improves reconstruction completeness by 20.5% and geometric accuracy by 32.8%. These results highlight the potential of semantic building model integration to advance GS-based reconstruction toward real-world urban applications such as smart cities and digital twins. Our project is available: https://github.com/zqlin0521/GS4Buildings.
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。
