We present the UrbanBIS benchmark for large-scale 3D urban understanding, supporting practical urban-level semantic and building-level instance segmentation. UrbanBIS comprises six real urban scenes, with 2.5 billion points, covering a vast area of 10.78 square kilometers and 3,370 buildings, captured by 113,346 views of aerial photogrammetry. Particularly, UrbanBIS provides not only semantic-level annotations on a rich set of urban objects, including buildings, vehicles, vegetation, roads, and bridges, but also instance-level annotations on the buildings. Further, UrbanBIS is the first 3D dataset that introduces fine-grained building sub-categories, considering a wide variety of shapes for different building types. Besides, we propose B-Seg, a building instance segmentation method to establish UrbanBIS. B-Seg adopts an end-to-end framework with a simple yet effective strategy for handling large-scale point clouds. Compared with mainstream methods, B-Seg achieves better accuracy with faster inference speed on UrbanBIS. In addition to the carefully-annotated point clouds, UrbanBIS provides high-resolution aerial-acquisition photos and high-quality large-scale 3D reconstruction models, which shall facilitate a wide range of studies such as multi-view stereo, urban LOD generation, aerial path planning, autonomous navigation, road network extraction, and so on, thus serving as an important platform for many intelligent city applications.

翻译：我们提出UrbanBIS基准数据集，用于大规模三维城市理解，支持实用的城市场景级语义分割与建筑级实例分割。UrbanBIS包含六个真实城市场景，共计25亿个点，覆盖10.78平方公里区域及3,370栋建筑，由113,346张航空摄影测量影像采集而成。该数据集不仅提供丰富城市对象（包括建筑、车辆、植被、道路及桥梁）的语义级标注，还提供建筑的实例级标注。值得注意的是，UrbanBIS是首个引入细粒度建筑子类别的三维数据集，涵盖不同建筑类型的多样化形态。此外，我们提出建筑实例分割方法B-Seg来建立UrbanBIS基准。B-Seg采用端到端框架，并配备简洁高效的大规模点云处理策略。与主流方法相比，B-Seg在UrbanBIS数据集上实现了更高的精度与更快的推理速度。除精心标注的点云外，UrbanBIS还提供高分辨率航空影像与高质量大规模三维重建模型，可支撑多视角立体匹配、城市LOD生成、航空航线规划、自主导航、路网提取等广泛研究，从而成为众多智慧城市应用的重要平台。