Contemporary architecture, as well as design, has revolutionised the approach to form creation, prioritising increasingly efficient and, above all, adaptive modelling. It is essential for designers to identify the requirements that the product to be realised must meet for its own production. This methodology, driven by technological advancements in the field of artificial intelligence (AI) and the use of advanced algorithms, enables the exploration and generation of optimised products from various perspectives based on chosen criteria; the resulting forms integrate functionality and aesthetics. This research proposes the use of tools within the parametric modelling environment Grasshopper, such as Galapagos and Octopus, which employ AI algorithms to enhance the design process and optimise forms for additive manufacturing. Experimentation with these plugins allows leveraging evolutionary algorithms to explore a wide range of design solutions, enabling designers to efficiently optimise complex forms. In this context, AI facilitates tackling multi-objective optimisation problems, improving parameters such as structural strength, material usage, and minimisation of printing times. This approach not only enhances the efficiency of the design process but also opens up new possibilities for innovation in design by integrating the advanced computational capabilities of AI with the creative potential of parametric design.
Advanced Digitization of Cultural Heritage via NeRF
Digitization processes, increasingly employed in various ways for the accessibility and preservation of cultural heritage, continuously engage with the diverse range of materials that define it. Objects like reflective ceramics and transparent glass have complex optical properties, which pose a unique challenge for digital acquisition methods such as photogrammetry and laser scanning, as well as for the modelling process. These materials often generate specular reflections or refract light, which interfere with the conventional algorithms used in the acquisition processes, leading to incomplete or inaccurate 3D models. This study explores the potential of Neural Radiance Fields (NeRF), an innovative 3D reconstruction technique based on deep learning, to overcome these limitations. By using volumetric encoding of scenes and simulating complex light interactions, NeRF captures phenomena like reflections and refractions with consistent realism. The exploration is carried out through a stress test on ceramic and glass materials, using both NeRF technology and traditional systems like digital photogrammetry. The comparison of the results highlights the advantages and disadvantages of both technologies, while emphasizing the current need for their complementarity, with workflows still largely hybrid.
Exploring Rapid 3D Heritage Asset Documentation: A Comparative Study of Laser Scanning and NeRF Algorithms in Museum Reconstruction
This paper explores the use of digital techniques for rapid surveys in cultural heritage, focusing on the creation of virtual environments for educational purposes. It compares two prominent methods for 3D reconstruction: laser scanning and AI-enhanced photogrammetry, particularly Neural Radiance Fields (NeRF). The case study centers on the virtual reconstruction of the Eccel Kreuzer Museum in Bolzano, South Tyrol, which involved documenting its original layout before an exhibition change. The research evaluates the performance of the Leica BLK laser scanner against the NeRF-based 3D models generated from video footage captured with an Insta360 ONE camera. While laser scanning provides high-quality results, the NeRF method, leveraging AI-based algorithms, offers a faster, cost-effective solution, particularly in environments with reflective surfaces and confined spaces. Despite challenges in accuracy and computational demands, the AI approach proves suitable for rapid documentation, especially when precision is less critical. The study highlights the advantages and limitations of both techniques, contributing to the ongoing development of 3D digital heritage assets that balance speed, cost, and quality in various applications such as VR and AR educational environments.
Exploring Alternative Urban and Architectural Virtual Realities Through Multidomain Digital Twins
The paper explores the use of multidomain Digital Twins (DTs) integrated with Virtual Reality (VR), GIS data, photogrammetry, configurational analysis, and AI-related approaches to support urban and architectural design exploration in historical contexts. The research develops a low-cost workflow combining spherical photogrammetry, point clouds, GIS integration, Space Syntax analysis, VR visualization in Unity, and immersive interaction to test alternative architectural hypotheses within their urban environment. The study investigates how VR-enabled DTs can function not only as visualization tools but also as cognitive and analytical devices for historical interpretation, urban analysis, configurational assessment, and design decision-making. The paper also discusses the future integration of AI methods such as NeRFs, semantic enrichment, and generative architectural sampling to automate reconstruction and support culturally sustainable urban design workflows.
Rapid and Low-Cost 3D Model Creation Using Nerf for Heritage Videogames Environments
The paper explores the use of Neural Radiance Fields (NeRF) for the rapid and low-cost creation of 3D heritage environments intended for educational videogames. The research focuses on reconstructing architectural heritage using 360-degree images and videos processed through Nerfstudio and Nerfacto workflows. Compared with traditional photogrammetry and laser scanning, the proposed approach aims to reduce acquisition effort while maintaining visually convincing reconstructions. The study demonstrates how NeRF-based pipelines can generate point clouds and meshes suitable for immersive heritage education, while also discussing limitations related to computational requirements and reconstruction resolution.
Automatic Virtual Reconstruction of Historic Buildings Through Deep Learning. A Critical Analysis of a Paradigm Shift
This paper critically examines the emerging use of artificial intelligence for the automatic virtual reconstruction of historic buildings, comparing it with traditional heritage reconstruction methodologies. The authors trace the historical evolution of reconstruction practices—from manual drawing, archaeological interpretation, CAD modelling, photogrammetry, and BIM—to current AI-based approaches founded on Deep Learning. The study focuses on Generative Adversarial Networks (GANs) trained to infer missing architectural parts from ruined structures, using synthetic datasets of Greek temples represented in multiple ruin states and reconstructed versions. A complementary Natural Language Processing workflow is also tested to improve segmented image generation and automate parts of the training process. Results suggest that AI can identify hidden formal and constructive patterns, generate multiple predictive alternatives, and support specialists in evaluating reconstruction hypotheses. At the same time, the paper warns that neural networks simplify architectural diversity into generalized stylistic rules and still depend on carefully designed datasets. The authors conclude that traditional scholarly expertise and AI prediction systems will likely coexist, marking a paradigm shift in how virtual reconstruction may be practiced in the near future.
Immersive Technologies for the Museum of the Charterhouse of Calci
The Charterhouse of Pisa in Calci, one of the most important monasteries in Tuscany, now houses two important museums: the Natural History Museum of the University of Pisa and the National Museum of the Monumental Charterhouse of Calci. While the Natural History Museum has recently enriched its collection by offering structured and differentiated visits based on user type, the offerings of the Museum of the Monumental Charterhouse are not sufficiently adequate to meet the great his-torical value of the complex. This contribution therefore presents the first results of a project aimed at enhancing visits to the National Museum of the Charterhouse using immersive technologies. The project envisages the definition of a new visit path, modifying the current path and integrating it with immersive experiences of video mapping, VR/AR, sound immersion, informative totems, audio–visual supports, and multisensory activities.
Phygitalarcheology for the Phlegraean Fields
The research investigates the theme of the valorization of the huge, but widespread, archaeological heritage of the Phlegraean Fields which, already weakened in its conservation and fruition by the bradyseismic phenomena of the area, is made even more fragile by the absence of narrative strategies, making even local communities unable to perceive its value. The study proposes a systematization of the knowledge of the Phlegraean Fields Park, through surveys and 3D models, integrated by the use of different digital technologies, which together promote effective forms of communication between users and heritage. Each site becomes the node of a network of thematic routes, traced starting from the major attractions of the area and aimed at defining a hybrid landscape, made of in site visits and immersive digital experiences. The goal is to generate a new model of inclusive museum, configuring cultural relationships between physically distant places, between lost spaces and real ruins.