Preface – Representation Across Boundaries New Links with AI, AI-GEN, and XR Tools for Cultural Heritage and Innovative Design
Representation Across Boundaries: New Paradigms in the Age of AI and XR
The introduction and rapid expansion of new algorithms based on Machine Learning (ML) and Deep Learning (DL) processes to support knowledge and design activities has revolutionized multiple domains in recent years. Among these, research in the fields of Cultural Heritage, Design, and Architecture is fostering the development of new methodologies for study and content creation — partly supporting existing tools and partly replacing them entirely — while offering a new paradigmatic perspective on the impact of AI within these domains.
More specifically, the introduction of Generative AI (GenAI) and the creation of new forms of content within these fields open new possibilities for the understanding, analysis, design, and communication of architecture and design. At the same time, these developments highlight the limitations and risks associated with their uncritical use and raise important ethical questions. Human guidance and supervision in generative processes still remain — fortunately — a foundational component of these workflows, ensuring control over results while encouraging their implementation across different areas.
Through a concise review of current research in the field, the article provides an updated overview of recent international studies, while anticipating possible future developments concerning XR and AI in Cultural Heritage, Design, and Architecture.
Index – Advances in Representation New AI- and XR-Driven Transdisciplinarity
Laser Scanning Data in Revitalization Projects for Historical Building
The paper investigates the integration of 3D laser scanning, point cloud processing, and HBIM methodologies for the revitalization and renovation of historical buildings. The research discusses how laser scanning technologies combined with BIM workflows can support the digital documentation, analysis, restoration, maintenance, and adaptive reuse of architectural heritage. Through the acquisition of high-precision point cloud data and the generation of HBIM models, the study proposes a workflow for managing architectural information, interdisciplinary collaboration, visualization, and renovation planning. The methodology also includes simulation analyses, digital archiving, and performance evaluation to improve communication, decision-making, and conservation processes in heritage renewal projects.
The Former Monastery of Saints Severino and Sossio: An Example of an Immersive Reality for the Dissemination of Cultural Heritage
The paper presents an immersive digital reconstruction of the former monastery of Saints Severino and Sossio, currently housing the State Archive of Naples, aimed at enhancing cultural heritage dissemination. The methodology integrates historical research, archival documentation, and multi-source digital survey techniques, including photogrammetry, laser scanning, LiDAR, and AI-based approaches such as NeRF and Gaussian Splatting. The resulting 3D model is implemented within a real-time interactive environment using Unreal Engine 5, where advanced rendering technologies (Nanite and Lumen) enable highly detailed and photorealistic visualization. The system is structured as an applied game, allowing users to navigate the architectural complex and explore its historical transformations through a timeline-based interaction. The research highlights the potential of AI-driven workflows and immersive environments to accelerate data acquisition, improve visualization quality, and support both analysis and dissemination of cultural heritage.
Preface: Introducing the Relationships Between Digital Representation and AR/AI Advanced Experiences Preface – Digital Innovations in Architecture, Engineering and Construction
Preliminary Study on Architectural Skin Design Method Driven by Neural Style Transfer
This paper explores the application of neural style transfer as an AI-assisted method for architectural skin design, aiming to enhance formal diversity and support conceptual design processes. The research investigates how convolutional neural networks can extract and recombine content and style features from different visual sources to generate alternative façade design proposals.
The methodology is based on the neural style transfer approach introduced by Gatys et al., implemented using a pre-trained VGG-19 network. As illustrated in the workflow diagram (Fig. 2, p. 744), the process defines content and style loss functions to iteratively optimize an output image that combines structural features from a content image with stylistic attributes from a reference image. The study applies this method to multiple sets of architectural images, including traditional Chinese buildings, modernist architecture, and urban skylines, combined with stylistic references such as Notre Dame, landscape painting, and science-fiction imagery. Results demonstrate that style transfer can generate diverse and visually suggestive façade configurations, supporting architects in the early design phase by providing rapid exploratory variations. However, the generated outputs remain conceptual and require further interpretation and development, highlighting the role of AI as a tool for inspiration rather than a deterministic design system.
Collaborative BIM-AR Workflow for Maintenance of Built Heritage
The research proposes a BIM-AR workflow to ensure the monitoring of the built heritage.Indeed, the application of AR might be an extension of the BIM since it allows during the on-site surveys’ phases to add and update punctual information within the BIM model overcoming the tradi-tional survey methods based on cards. Consequently, the information models can act as collaborative tools at the service of public autorithies and stakeholders, thus supporting an efficient building man-agement, also from a preventive perspective. The research is a development based on the results of the Fondamenti di modellazione BIM per il settore delle costruzioni[1] academic course of the master’s degree course in Ingegneria Edile-Architettura [2] of the University of Padua. Starting from the students’ BIM models, the workflow exposes the integrability of the AR during the on-site survey campaigns of a case study to verify the geometric accuracy and the structural problematics of the BIM models overlapped to the real buildings by recording the information directly on them.