ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds

TL;DR

This paper introduces ARCH2S, a new dataset and benchmark for semantic segmentation of outdoor architectural point clouds, addressing limitations of existing datasets with detailed annotations and diverse real-world building types.

Contribution

It provides a semantically-enriched, photo-realistic 3D architectural models dataset with 14 classes, covering various building purposes and landscapes, for improved outdoor segmentation research.

Findings

New dataset with 4 building purposes and 14 semantic classes

Benchmark for outdoor architectural point cloud segmentation

Addresses privacy and annotation cost issues in existing datasets

Abstract

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.