arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.06337cs.CV
收藏

BuildingWorld:面向城市基础模型的结构化三维建筑数据集

BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models

Shangfeng Huang, Ruisheng Wang, Xin Wang

AI总结:

BuildingWorld通过构建包含约五百万个LOD2建筑模型及LiDAR点云的全球多样化三维建筑数据集,并引入Cyber City虚拟城市模型和标准化评估指标,解决现有数据集建筑多样性不足的问题,以支持城市基础模型的训练与评估。

摘要:

随着数字孪生成为现代城市转型的核心,准确且结构化的三维建筑模型成为高保真、可更新的城市表征的关键使能因素。这些模型支撑着包括能源建模、城市规划、自主导航和实时推理在内的多种应用。尽管三维城市建模近期取得进展,但大多数基于学习的模型是在建筑多样性有限的数据集上训练的,这显著削弱了它们在异构城市环境中的泛化能力。为解决这一局限,我们提出了BuildingWorld,一个全面且结构化的三维建筑数据集,旨在弥合风格多样性方面的差距。它涵盖来自地理和建筑上多样化地区的建筑——包括北美、欧洲、亚洲、非洲和大洋洲——为城市尺度的基础模型建模与分析提供了具有全球代表性的数据集。具体而言,BuildingWorld提供了约五百万个从多种来源收集的LOD2建筑模型,并配有真实和模拟的机载LiDAR点云。这使得三维建筑重建、检测与分割的全面研究成为可能。我们还引入了虚拟城市模型Cyber City,以生成具有定制化和结构多样化点云分布的无限训练数据。此外,我们提供了针对建筑重建定制的标准化评估指标,旨在促进结构化三维城市环境中大规模视觉模型和基础模型的训练、评估与比较。

英文摘要:

As digital twins become central to the transformation of modern cities, accurate and structured 3D building models emerge as a key enabler of high-fidelity, updatable urban representations. These models underpin diverse applications including energy modeling, urban planning, autonomous navigation, and real-time reasoning. Despite recent advances in 3D urban modeling, most learning-based models are trained on building datasets with limited architectural diversity, which significantly undermines their generalizability across heterogeneous urban environments. To address this limitation, we present BuildingWorld, a comprehensive and structured 3D building dataset designed to bridge the gap in stylistic diversity. It encompasses buildings from geographically and architecturally diverse regions -- including North America, Europe, Asia, Africa, and Oceania -- offering a globally representative dataset for urban-scale foundation modeling and analysis. Specifically, BuildingWorld provides about five million LOD2 building models collected from diverse sources, accompanied by real and simulated airborne LiDAR point clouds. This enables comprehensive research on 3D building reconstruction, detection and segmentation. Cyber City, a virtual city model, is introduced to enable the generation of unlimited training data with customized and structurally diverse point cloud distributions. Furthermore, we provide standardized evaluation metrics tailored for building reconstruction, aiming to facilitate the training, evaluation, and comparison of large-scale vision models and foundation models in structured 3D urban environments.

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。

↑