Cultural Heritage has been significantly impacted by advancements in the Information and Communications Technology domains, which have inspired a strong multidisciplinary interest and enabled the development of innovative strategies for the preservation, management, and enhancement of the heritage itself. Notably, the digitisation process, which entails the acquisition of 3D data obtained through cutting-edge LiDAR and photogrammetric scanning techniques, is set up as an advantageous tool for producing an accurate representation of the historical buildings. In addition, point clouds and reliable HBIM models have caught the minds of the architectural community, and are now receiving huge backing from Artificial Intelligence. Such support is provided by procedures that link semantic features to structural and decorative elements. In this scenario, the following research is presented: the aim is to test an automated iterative process within a scan-to-BIM methodology, starting from automatic point cloud segmentation operations with open-source, model-fitting algorithms. This method will prove to be a solid support for the final phase of the 3D parametric/adaptive reconstruction that’s also compatible with BIM Authoring. The study focuses on various masonry vaulted systems. These types of structures are first examined using ideal models, which were perfectly discretised and set up by the user, and then employed as a starting point for validating the parameters of the RANSAC algorithm on point clouds acquired by laser scanners. These latter ones nevertheless have irregular geometries, making comprehension, analysis, and management far more challenging.

The ScanToBIM approach represents an established methodology for the digitization and integrated management of historic building heritage. However, the reconstruction process of building and architectural elements, especially in HBIM, is still a significant challenge, both because of the inherent geometric complexity and the need to preserve the detail and semantic coherence of the produced digital models. This paper specifically addresses the problem of semi-automated three-dimensional generation of historic architectural elements through a parametric three-dimensional genesis process. The study was applied to the Aragonese Tower of Bitonto (Bari), an imposing structure along the city's medieval wall perimeter. The tower, with a circular plan and three vaulted levels connected by fortified corridors includes late 15th-century casemates and fortifications inspired by the designs of Francesco di Giorgio Martini. Described in 1503 as one of the strongest fortresses in the Kingdom of Naples, it was later used as a prison. The proposed approach integrates artificial intelligence-based algorithms for semantic segmentation of elements and their subsequent optimization. Particular attention is paid to the relationship between surface visual information and its narrative, stylistic, and technological functions, with the classification of elements aligned with the Industry Foundation Classes (IFC) standard. The consistent assignment of geometric and semantic data enhances the interoperability of digital models, supporting their application in the restoration and heritage management of historic buildings. The results obtained from the applied process show the possibility of integrating advanced automation and validation technologies into a complete BIM process, guaranteeing geometric correctness and the preservation of fundamental stylistic details of the historical architectural heritage in the realization of the 3D digital model.