Cross-domain urban and heritage point cloud benchmarks for semantic segmentation: insights from the 3M (Mapping Mappano Municipality) and ArCHX datasets

Abstract. Semantic segmentation of 3D point clouds is a key enabler for intelligent urban analysis and cultural heritage documentation. However, current benchmarks remain uneven for different reasons: from the fragmented scenes of cityscape scenarios where a unique environment is not provided, to the difficulties in representing the great variety of architectural styles and lexicons in the cultural heritage (CH) domain. This study introduces two complementary datasets, the 3M (Mapping Mappano Municipality) dataset and the ArCHX (Architectural Cultural Heritage eXpanded) dataset, meant to enhance cross-domain learning between urban and architectural heritage environments. The 3M dataset, derived from UAV photogrammetry and GNSS-based surveys over an 11.9 km² area near Turin (Italy), provides a highly accurate, semantically labelled urban point cloud (~900 M points) suitable for urban planning, automatic mapping, and infrastructure design. In parallel, the ArCHX dataset extends the existing ArCH benchmark with new scenes from Portuguese masonry gates and Indian Nagara-style temples, reaching over 400 million points. These additions diversify architectural typologies and improve the generalisation capacity of AI models applied to heritage semantic segmentation tasks. Methodological challenges in harmonising class taxonomies, managing heterogeneous materials, and aligning cultural architectural semantics across datasets are eventually discussed. Collectively, the 3M and ArCHX datasets establish a novel foundation for cross-domain benchmarking in 3D semantic segmentation, advancing data-driven research in digital twins, mapping, Historic Building Information Modelling (HBIM), and AI-assisted heritage documentation.