Digitization of Cultural and Museum Heritage represents one of the most engaging challenges that would ensure a sustainable and ethical approach for next generations; digital technology’s pervasiveness imposes a comprehensive management of architectural heritage by producing facsimiles of buildings and artworks and by testing robust methodologies, with the final result of providing effective multipurpose models. In this context, the main goal of the present paper is to develop a semantically aware HBIM model that includes an intelligent objects parametrization, leveraging Extended Reality (XR) technologies and digital curation of contents to pursue the preservation of Cultural Heritage (CH) as a whole. This research is implemented in the case study of the Ducal Palace of Urbino that houses the National Gallery of Marche. It was chosen as a remarkable example of a museum located in an architectural complex with a relevant historical background and fine detail of shapes and mouldings. In Italy, as in other European scenarios, museums and their collections need suitable dissemination and management systems that take advantage of the recent digital paradigms. The challenging approach is to exploit existing platforms and software and to adopt a cognitive modelling process, able to develop tools supporting managers and museum curators while enabling user experiences using immersive and interactive features. In order to stress the workflow, this work proposes the use of families with high Level of Detail (LOD) and high Level of Information (LOI). The present article provides, as well, an accurate data enrichment process specifically designed for a gallery’s artworks such as paintings and sculptures, in line with the national and international policies. The study presents a robust and reproducible methodology for digital musealization and management, focusing, as future overall objectives, towards a greater merging between the HBIM approach and XR technologies, also facilitated by training new professional figures with more in-depth digital skills.

Historical heritage is demanding robust pipelines for preserving, enhancing and disseminating its prominent value. Semantic segmentation of 3D Point Clouds has gained increasing attention over the years, since it might assist in automatically recognizing historical architectural elements. Nonetheless, semantic segmentation is particularly challenging in Cultural Heritage (CH) domain, due to the shapes complexity and the limited repeatability of elements across different architectures, which strengthens the difficulty to define common patterns within the same class of elements. Besides, as Deep Neural Networks demand an appreciably amount of labelled data to be trained, but the lack of available annotated heritage point clouds prevent the research in this direction. To tackle these issues, in this paper it is proposed a Deep Learning system able to recognize historical building elements by leveraging synthetic point cloud. The generation of the 3D models, vaults, is based on a procedural modelling approach that follows the ideal shapes, according to the rules of descriptive geometry for the main types of vaults. The approach has been applied to a newly synthetic dataset which is publicly available. This dataset comprises 6 labelled points clouds, derived from a comprehensive ontological taxonomy in order to describe an univocal and robust architectural hierarchy: barrel vaults, groined vaults, mirror vaults, barrel vaults with cloister heads and lunettes, barrel vaults with lunettes, sail vaults. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the proposed approach.