ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds
This addresses a data scarcity problem for researchers and practitioners in computer vision and architecture, providing a new benchmark for semantic segmentation of exterior architectural structures.
The paper tackles the lack of detailed outdoor 3D point cloud datasets for architectural exteriors by introducing ARCH2S, a semantically-enriched, photo-realistic dataset and benchmark for semantic segmentation, featuring 4 building purposes and 14 semantic classes from real-world buildings in Hong Kong.
Precise segmentation of architectural structures provides detailed information about various building components, enhancing our understanding and interaction with our built environment. Nevertheless, existing outdoor 3D point cloud datasets have limited and detailed annotations on architectural exteriors due to privacy concerns and the expensive costs of data acquisition and annotation. To overcome this shortfall, this paper introduces a semantically-enriched, photo-realistic 3D architectural models dataset and benchmark for semantic segmentation. It features 4 different building purposes of real-world buildings as well as an open architectural landscape in Hong Kong. Each point cloud is annotated into one of 14 semantic classes.