XR (extended reality) environments have driven professionals in the construction industry to adopt advanced digital surveying and 3D modelling techniques, improving project quality and site management through enhanced visualization, accuracy, and precision. Photogrammetry and laser scanning have been crucial in the scan-to-XR process, enabling the development of digital twins (DT) throughout the construction lifecycle. However, converting survey data into usable models for immersive experiences requires expertise in digital representation and software development. Digital representation transforms raw data into functional models, yet challenges remain. Survey outputs typically feature high polygon counts for detail, which can overload XR applications, causing slowdowns and reducing fluidity, especially on devices with limited resources. Additionally, high-resolution textures further strain computational power and memory. Optimising these textures is key to balancing visual quality and performance. XR platforms like Unity and Unreal Engine demand specific rendering standards, and non-optimised models can fail to meet these, requiring further adjustments. This study aims to develop a pipeline for creating high-fidelity DTs of an ongoing construction site. Data is collected through photogrammetry and laser scanning, followed by model optimisation for XR applications. The optimised model is integrated into real-time platforms for interactive use, producing both VR and web-XR models. This pipeline will aid in construction-site management, safety inspections, and communication between stakeholders, contributing to DT technology and to the efficiency of the construction industry.
Evaluating Urban Perception: Using Explainable Machine Learning Predict Through the Best Pipeline
Understanding subjective urban experiences is essential for designing cities that enhance well-being. Urban design should account for the psychological effects of environments on individuals, as these significantly shape perceptions and behaviors. However, a major challenge is the limited availability of urban perception data. Recent studies have leveraged large, crowdsourced datasets like Place Pulse 2.0 (PP2) to inform machine learning (ML) models for urban perception prediction, but the accuracy and reliability of outcomes remain underexplored. There is a critical need to evaluate whether these datasets truly capture human perceptions. This study investigates the role of urban street images in understanding environmental perceptions, using the PP2 dataset and ML techniques. It explores various ML pipelines, employing TPot AutoML for model selection and 5-fold cross-validation to prevent overfitting. The goal is to identify the most efficient model that strengthens the link between automated predictions and human perception. The study also applies SHAP (SHapley Additive exPlanations) to interpret model outputs, revealing feature importance and interactions. This improves transparency and ensures ML-generated insights are actionable for urban planning. By rigorously testing ML pipelines, this research enhances predictive accuracy and contributes to the development of reliable urban design tools. The findings highlight ML’s potential in processing large-scale perception data, uncovering hidden patterns, and informing people-centered urban planning. However, further validation against real-world surveys is necessary to ensure robustness and generalizability in assessing urban perceptions.
Advanced Deviation Analysis Visualization for BIM in Heritage Environment
This paper presents a methodology leveraging modern technologies such as BIM, laser scanning, and virtual reality to address challenges in maintaining historical buildings. The focus is on a scan-vs-BIM deviation analysis workflow, enabling the identification of modelling inaccuracies and structural issues by comparing HBIM models with point-cloud surveys. The proposed approach facilitates decision-making processes by providing an accessible and detailed visualization of results. The methodology begins with a structured BIM model and a corresponding point cloud. Using Autodesk Revit and a tailored Dynamo script, distances between building elements and their surveyed points are calculated and organized for compatibility with various platforms. The results are then transformed into interactive 3D visualizations using Python, where points are spatially and color-coded based on deviation values. The workflow integrates immersive technologies, such as virtual reality, to explore the results interactively and at real scale, enhancing insights beyond traditional 2D graphs and screen-based methods. This immersive visualization highlights critical details and supports improved decision-making in structural analysis and conservation efforts. The paper also discusses the potential for augmented reality to further enhance these visualizations, offering direct comparisons between BIM models, point clouds, and the physical building. With a BIM-based and open-source approach, the methodology ensures broad accessibility and reusability, making it a robust tool for deviation analysis and visualization in heritage conservation projects.
“Campus delle Architetture, del Design e della Pianificazione” Project: WebAR for Public Engagement
The design of the Politecnico di Torino “Campus delle Architetture, del Design e della Pianificazione” has an enormous strategic value, both for the reorganisation of the University and for the city dynamics, contributing to the overall development of the Po cultural axis. The transformation involved by the new campus will significantly impact the life of the area, radically changing its intensity through the daily flows of thousands of people and making the park an actual natural connective tissue. The communication project includes the realisation of events aimed at presenting the Campus to disseminate and popularise the outcomes of the realisation process to different stakeholders, showing a scale model of the area. Among the innovative features of the communication proposal is the superimposition of digital layers on the physical model for audience engagement through a webAR that activates a step-by-step journey with descriptions of different aspects of the campus project.
Extended Reality for Museums and Exhibit Design: Experiences in Didactic Activities
The paper illustrates the didactic activity of the introductory seminar Inside the Museum, held since 2021 for the master’s degree courses of the Department of Architecture and Design (DAD) at the Politecnico di Torino. The paper describes the innovative character undertaken during the seminar and how it has evolved in parallel with the digital transition that has affected education and cultural heritage. The central theme of the seminar is the relationship between digital technologies and museum institutions, which was investigated according to a multidisciplinary approach involving the disciplines of drawing and representation, together with the themes of exhibit design and museography addressed through Extended Reality as the communicative medium of the project design. The main applications used for the teaching activity were web-based tools for creating virtual, immersive, and augmented reality experiences. Video storytelling, a passive entertainment-oriented product, 360° virtual tours allowing interactive enjoyment, and HeritageMaps, used for developing interactive maps with georeferenced content, were addressed. Starting from low-cost and sustainable web-based solutions, the latest activities experimented with the customization of AR applications using Unity and Vuforia Engine tools.
An Educational Experience Between AI and Architectural Drawing
This paper presents the latest phase of a research project investigating the interplay between the representation of ‘Virtual Living’ and digital technocultures—particularly the integration of Artificial Intelligence (AI) and Extended Reality (XR)—within the educational framework of an Architectural Drawing course. This course is part of the third-year curriculum of the Bachelor’s Degree in Architecture at the ‘G. d’Annunzio’ University of Chieti-Pescara. The research builds upon and refines technocultural methodologies long employed in teaching, leveraging the concept of the ‘semantic model’ as a versatile foundation for designing habitable virtual spaces, such as metaverses or virtual museums. This approach has been revisited and expanded to address the rapid evolution of generative AI applications, which demand rigorous monitoring and continuous thematic experimentation. New technologies in representation are reshaping the pedagogical landscape, offering unprecedented opportunities to redefine the scope of architectural drawing education. From descriptive geometry to surveying, from the history of representation to design, the incorporation of AI has fundamentally transformed how visual representations are conceived and executed. This paper discusses a case study that bridges research and pedagogy, showcasing how students’ creativity, when coupled with the capabilities of AI, facilitates the creation of innovative semantic models. These models have direct applications in the design of Virtual Cities and Museums, offering a vision of inhabitable spaces within the metaverse.
Impact of Varying Street View Perspectives on Urban Perception: The Case of Celoria Street in Milan
Urban environments significantly influence people’s perception and walkability. Advances in computer vision and the availability of open-source Street View Imagery (SVI) have increased the use of Google Street View (GSV) for perceptual predictions and walkability assessments. However, a critical issue arises from the discrepancies between GSV images, captured from street centerlines, and SVI taken from pedestrian perspectives on sidewalks. This study examines whether people’s perceptions and street element proportions derived from GSV images align with those from sidewalk viewpoints, providing a more accurate basis for urban studies. Taking Celoria Street in Milan as a case study, two sets of 360° panoramic images were collected, one from the street center and the other from the sidewalks. These images were processed using a pre-trained perception prediction model and image segmentation techniques to generate perception responses. Dynamic Time Warping (DTW) was applied to assess the consistency between the two datasets, while Ordinary Least Squares (OLS) regression was used to analyze the impact of viewpoint changes along the street scene. Findings indicate that differences in sampling perspectives can affect urban environment assessment and perception predictions. This study highlights the potential biases of GSV data for analyzing urban environments and perceptions, advocating for more cautious use of SVI to ensure robust predictions on urban perception and walkability.
XR in Serious Games an Application on Palazzo Barberini
This paper presents a scientifically controlled method for developing serious games focused on architectural heritage, emphasising their role in enhancing and popularising cultural assets. The study stems from work carried out during the PhD Course in History, Representation, and Restoration of Architecture, using Palazzo Barberini in Rome as a case study. By focusing on its outdoor spaces and façade, the research tested an operational workflow and addressed challenges in its implementation. Unlike other cultural assets, architecture requires a cognitive approach reflecting its experiential nature, as “architecture is like a great sculpture carved into which man penetrates and walks” [1]. Extended Reality (XR) technologies were applied to recreate this experience. The Serious Game for Palazzo Barberini integrates both interchangeable in situ and remote gameplay modes. Virtual reality enables immersion and spatial comprehension remotely, while augmented reality enhances interaction on-site. These technologies transform users from passive observers into active participants, fostering experiential learning and deeper engagement with cultural heritage. The game’s development relied on comprehensive digital surveys to ensure formal and spatial consistency with the architecture. Panoramic photographs and graphic enhancements were used to create interactive panoramas designed to spark curiosity and emotional engagement. In conclusion, combining serious games with XR proves highly effective for cultural enrichment and edutainment. This approach enhances accessibility, promotes both entertainment and education, and preserves the authenticity of cultural assets.
Txt2city. From the Prompt to the City’s Image
In the urban sphere, AI is often associated with the concept of smart cities and thus the use of technology and the enormous computing power of machines to increase the quality of life for citizens, creating greater efficiency in resources and services, but there are further applications. The sprawl of information technologies is changing relationships between people and space, contributing to the mutation of iconographic production and the way content is conceived and communicated. Digital management and communication processes focus on images. The set of images constitutes a highly evocative language; it can be immediately comprehensible or require decoding that refers to specific contexts and cultures. Their importance is evident in human-targeted communication, but they also constitute a data transmission vehicle for empirical knowledge generation by algorithms like those used for artificial image creation from other images. Text-to-image AI generators are trained through the analysis of hundreds of millions of images and their related textual descriptions, which allows the system to learn the relationship between text and visual elements. Through this process, the network is also able to infer other information about reality. Images can be the representation of actual objects, as well as a subjective product of imagination or sensory processing. So too are the images created by Italo Calvino’s Invisible Cities, which bear witness to mental and non-geographical spaces. Cities that cannot be seen can be constructed from their poetical descriptions. What textual variables affect the realization of an image? How do the datasets that different text-to-image tools draw on affect image realization? Can these tools be trained from the user’s realization of an image? The paper collects the first outcomes of a research project comparing the results produced by the main image-generation tools from text descriptions extracted from Calvino’s book.
The Sacred Space Dimension. Interactive Digital Narratives for the Scuola Grande di San Marco in Venice
The essay focuses on the valorisation of pictorial works to be brought back into their original exhibition contexts, reflecting on the contribution of today’s digital technologies in enhancing their understanding and enjoyment. Starting from this assumption, the focus is on the principles of digital storytelling to be implemented in installations capable of maintaining a continuous dialogue between physical and digital space, through video projections interacting with reconstructions of 3D-printed architecture, obtained through careful perspective restitutions. In particular, there are three canvases depicting some of the most important events in the life of Saint Mark, painted by Gentile and Giovanni Bellini and by Giovanni Mansueti, respectively for Guardian Grande Marco Pellegrini and Jacopo Dardani. They were once kept in the Sala dell’Albergo of the Scuola Grande di San Marco in Venice, where their return is now hoped for. The multimedia installation planned for the Sala Capitolare is thus configured as an edutainment route that anticipates the rediscovery of the original works, to be contemplated only after understanding their specific meanings.