This study evaluates the performance of three image-based 3D reconstruction methods—Structure-from-Motion with Multi-View Stereo (SfM-MVS), Neural Radiance Fields (NeRF), and Gaussian Splatting (GS)—for documenting Architectural Heritage (AH). Data acquisition was conducted using low-cost sensors: a drone to capture the stone portal of the external façade and a 360° camera to document the interior spaces. NeRF and GS significantly outperformed SfM-MVS in processing time, with NeRF excelling in reconstruction completeness. However, GS faced challenges with point number control, and NeRF reconstructions exhibited artifacts and noise, particularly on flat surfaces. Accuracy assessments, using TLS point clouds as a benchmark, revealed that SfM-MVS provided the highest geometric precision for the external façade, despite minor gaps in reconstruction. In contrast, NeRF and GS fell short of the accuracy required for precise geometric documentation, with NeRF exhibiting prominent artifacts in flat or poorly detailed regions. Interior reconstructions were further limited by the higher Ground Sampling Distance (GSD) caused by the technical constraints of the 360° camera and the increased capture distance for elevated areas. In conclusion, we can affirm that while NeRF and GS demonstrate strong potential for visualization due to their rendering quality and efficiency, SfM-MVS remains the most reliable method for achieving accurate geometric documentation of AH.

The paper stresses the potential of digital technology in the field of Cultural Heritage (CH), focusing on Architectural Heritage (AH) conservation and management process. It presents a workflow based on non-parametric automatic 3D modeling and Industry Foundation Classes (IFC) authoring to combine geometry and semantic information. The goal of such a methodology is to overcome time-consuming manual tasks that still limit the Historical Building Information Modelling (HBIM), which nevertheless proves to be one of the most effective digital tools for the conservation and management of AH in the medium to long term. The proposed workflow consists of five steps: the 3D survey campaign and raw data processing, the semantic annotation of images according to different information layers, the annotation transfer from images to the point cloud representing the studied architecture, the obtained Point Cloud Information Model (PCIM) automatic segmentation and 3D mesh wrapping, and finally the IFC generation for the HBIM representation. This unconventional digital chain was tested to support the knowledge representation of Villa Leonardi, an historical house in the Marche Region (Italy). The final output is a 3D model of the building, automatically processed from digital survey data, and semantically enriched thanks to the material consistency and decay analysis carried out and annotated on spherical panoramas. The effectiveness of this approach was proven in the conservation project for the façades of the house: enriched data on materials and decay supported an action plan of restoration works, which was then recorded in the HBIM model, thus permitting time and cost control.

Digital technologies enable a thorough analysis of Architectural Heritage, offering various representations that provide different levels of documentation and knowledge-based conservation tools. This paper presents a methodological approach that leverages three digital representations related to three levels of documentation: Virtual Tour Informational Modelling, Point Cloud Informational Modelling, and Historical Building Information Modelling. Their characteristics and potential are compared, focusing on the effectiveness in supporting the analysis process, and the management of future conservation works. Furthermore, the dichotomy between 2D and 3D representations of AH is tackled, emphasizing the need to align with the conservation strategies, timeline, and budget constraints. It also discusses the integration of heterogeneous data and various digital representations to address the challenges in AH preventive conservation and management, resulting in the proposal of a sustainable documentation workflow to support the conservation process.

The paper presents the digital representation and virtual experience of Borgo Storico Seghetti Panichi, a cultural site distinguished by the close interplay between architecture and landscape. The project was developed using an integrated approach that brings together 3D survey techniques, immersive technologies, and Artificial Intelligence (AI). Consolidated techniques such as Terrestrial Laser Scanning (TLS) and UAV-based photogrammetry were adopted to generate accurate 3D models of the Villa, the Roccolo, the Church, and the surrounding historic park. Moreover, preliminary tests with 3D Gaussian Splatting (GS) were conducted to evaluate its potential for photorealistic and real-time visualization in Cultural Heritage (CH) contexts. The different digital representations were embedded in a Virtual Reality (VR) application designed to offer an engaging and educational user experience. The immersive environment includes interactive components such as the digital replicas of the buildings and the historic park, audio narration, and a virtual keyboard connected to a Large Language Model (LLM). This system enables users to formulate questions in natural language and receive dynamic, context-specific responses within the VR environment, fostering active learning and customized exploration. The development process included a structured pipeline from survey data to VR implementation, with specific focus on optimization for standalone headsets. User evaluation tests confirmed the effectiveness of the experience in terms of realism, interaction, and accessibility, while also identifying areas for further improvement.

This study presents a methodology integrating above-ground and underground 3D survey data within a Heritage Building Information Modeling (HBIM) framework, further developed into an eXtended Reality (XR) environment. The historic centre of Cagli (Italy), with its stratified architectural and archaeological layers, served as a pilot case. Data acquisition included Terrestrial Laser Scanning (TLS), UAV photogrammetry, and 3D Ground Penetrating Radar (GPR), producing detailed georeferenced datasets of buildings and subsurface anomalies. These were modeled as parametric volumes in an HBIM environment and enriched with structured metadata, including geometry, historical sources, and risk information. The HBIM model was seamlessly integrated within an XR application built in Unity and connected with Google Cloud services, enabling real-time data exchange. Users can interact with the 3D model using a Mixed Reality (MR) headset, accessing metadata and uploading new information on-site. The system supports scenarios such as post-earthquake assessment by associating building records with standardized forms. Results demonstrate the potential of connecting HBIM with XR not only for enhanced visualization, but also for collaborative heritage management in situ. Integration allows for intuitive, data-driven exploration of complex heritage layers, facilitating decision-making processes and opening new perspectives for monitoring, documenting, and engaging with historic urban environments. The proposed workflow is replicable and adaptable to other historic villages, which, despite their unique identities, often pose similar conservation challenges due to their layered complexity and vulnerability.