Text-to-image systems based on generative pre-trained transformers have become pervasive in recent years. This result is mainly due to the generation tools’ ease of use, application availability, and increasingly refined graphical and algorithmic capabilities. On the other hand, the non-controllability given by a random process and the dependency on existing information databases highlight some limitations of these automatic image-generation methods. The rapid construction of increasingly realistic digital images draws new boundaries between real and unreal, highlighting a strict relation between text and image regarding semantics and logic descriptions. Therefore, a critical look into the use of these applications as tools for a reliable representation of architecture becomes cogent. We started from representations established by the treatises, as in the case of architectural orders. Most of these drawings, proportions, and rules are derived from descriptive parts in Vitruvius’ text. However, the graphic interpretations result from the architect’s experience and culture, which has become the basic grammar of architecture. This research stems precisely from the connection between Vitruvius’ text, the new text-to-image contents, and the established representations of the treatise writers. The comparison considers both image reliability and geometric rules, testing the current potential of GPT systems for image creation and reliability.
The Connection Between Scenography and Virtual Reconstructions of the Statuary Groups in the Nymphaeum of Tiberius
The paper investigates the relationship between spatial scenography and virtual reconstruction in the interpretation of fragmented archaeological contexts. Focusing on the Nymphaeum of Tiberius, the study combines historical research, integrated digital survey (laser scanning and photogrammetry), and 3D modeling to reconstruct both the architectural environment and its original statuary groups. Through processes of virtual anastylosis and multidimensional representation, fragmented sculptures are digitally reassembled and repositioned within their original setting. The resulting models are used in extended reality environments and web-based platforms to enhance interpretation, enabling users to explore the reconstructed spatial narrative and understand the original scenic composition of the site.
AR for Virtual Restoration
This paper explores the use of Augmented Reality as a tool for virtual restoration and interactive museum communication. Within the OSTIA 3D Project, the authors develop a workflow combining 3D acquisition, digital modelling, restoration hypotheses, and AR visualization to enhance archaeological heritage without physically altering original artifacts. The study focuses on the digital reintegration of damaged sculptural works preserved in the Archaeological Park of Ostia Antica, aiming to restore perceptual unity while maintaining historical authenticity. Through photogrammetry, structured-light scanning, mesh editing, reverse engineering, and geometric validation, missing portions are virtually reconstructed and presented through an AR application built in Unity. Users can compare the original object, the restored version, and segmented additions while accessing images, texts, and contextual information. The research demonstrates how AR-based virtual restoration can improve accessibility, emotional engagement, and public understanding of fragmented archaeological objects in museum environments.
Storytelling for Cultural Heritage: theLucrezio Menandro’s Mithraeum
The essay is part of the valorization for the knowledge of Cultural Heritage and is articulated ac-cording to three different readings: a first semantic reading, concerning the meaning of narration of a specific “story”; an operational reading in which the proposed methodology is applied to a concrete case study; a reading on the possible scenarios of communication for knowledge, using AR. The first results of the ongoing digitization process of the collection inside the buildings of the Ostia Antica Archaeological Park in Rome are presented here, where innovative digitization and data optimization technologies are compared with the immense heritage of the Park, animating the exhibition-inter-active itinerary, creating digitally usable content through AR, reflecting on the opportunity of these technologies to create new forms of digital storytelling for use and knowledge.