3D technologies for cultural heritages

A Roman village was recently found in Ono San Pietro, in the Mid Valle Camonica (Italy), including the rests of four rustic buildings with basement room. In one of these buildings two iron objects were found, attributable to the metallic parts of a wagon wheel. In particular, they were identified as a bushing mounted inside the wheel hub to prevent wear, and a rim mounted on the external diameter of the hub to prevent radial cracking. First, these finding were digitalized by laser-scanning, to study and measure them in detail without handling. The study of the virtual findings allowed hypothesizing their role, the concept behind their design, as well as the possible techniques used for their manufacturing. Based on the size of the findings, a reconstruction of the wooden wheel they could be mounted on was made. By means of structural analyses, the load capacity of the axle was determined, and from this a possible configuration of the wagon assembly was derived, also considering the orographic conformation of the site. By means of this reverse engineering procedure, a possible scenario of the freight transport in Mid Valle Camonica during the Roman Age was obtained.

Keywords: Laser Scanning , Reverse Engineering , Roman Age , Wagon Wheel

This study investigates the archaeological significance and preservation state of the Lombardo, a XIX century paddle steamer closely associated with Garibaldi's Mille Expedition and now resting off the Tremiti Islands. The research aims to contextualize the vessel's historical role and to reconstruct its steam engine, paddle wheel and shipwreck dynamics, providing the first comprehensive three-dimensional documentation of the site. Underwater photogrammetry was carried out using high-resolution imaging, a dedicated geodetic network of coded markers, and Structure-from-Motion workflows to generate a scaled 3D model of the wreck. Historical and technical sources were also examined to identify the original configuration of the steam engine and paddle wheel. The results show a highly fragmented site distributed between 9 and 22 m depth, where the surviving remains corroborate historical accounts of post-wreck salvage operations and subsequent natural collapse processes. Analysis of the wreck reveals that the ship's steam engine was a Maudslay Siamese double-cylinder type, driving radial paddle wheels. The distribution of the remains also suggests that the vessel originally settled on its port side, oriented along a north–south axis. The conclusions demonstrate how integrated archaeological, geomatic, and archival methods could clarify the technical characteristics of the Lombardo and improve understanding of its post-depositional transformation, providing a robust basis for future conservation and dissemination activities.

Keywords: Italian Risorgimento , marine steam engine , maritime archaeology , shipwreck , underwater heritage , underwater photogrammetry

This paper presents a comprehensive overview of methodologies developed to support blind and visually impaired people (BVIP) in perceiving two-dimensional visual content through tactile representations. Over the past decade, the TIP group at the Department of Industrial Engineering of Florence has advanced both deterministic and AI-assisted techniques to generate tactile bas-reliefs from pictorial and technical images. The research spans various computerassisted methodologies for producing depth images or full 3D models of tactile supports. The research seeks to establish a codified language, its expression dictated by the ‘grammar' of semi-automatic procedures that offer limited scope for a manual user's free interpretation. Latest results achieved in the translation of abstract paintings are presented, including an effective pixel intensity-based approach for translating chromatic information into tactile depth. Applications include cultural heritage accessibility and inclusive technical education. Results demonstrate the growing viability of hybrid and AI-enhanced solutions to generate meaningful, perceivable tactile models, highlighting the importance of structured tactile languages and multimodal interfaces for improving accessibility.

Keywords: 3D modelling , bas-relief , Blind People , Depth image , tactile models

This study investigates how the immersion level, experienced by users during their interaction with a virtual museum application, affect Visitor Experience and Learning Performance. A between group experimental study, has been conducted in a laboratory setting. A total of 60 participants has been randomly divided in two groups (A and B). Group A used a virtual museum application to interact with two digital replicas of archaeological finds via a low immersive desktop-based interface. Group B interact with the same application using a high immersive HMD-based interface. Immediately after the interaction with the VR application, participants were asked to answer a questionnaire in order to measure their perceived visitor experience (VX), their attitude toward the experience and their learning performance in terms of immediate knowledge retention. The results suggest that the use of HMD-based interface can improve the quality of VX and the attitude toward the experience reported by the participants, but it can negatively affect the resulting learning outcome. These findings emphasize the need for museum curators to find a balance between utilizing technology for attract new visitors and preserving the educational value of the exhibits.

Keywords: Immersion , Learning Performance , Virtual Museum , Virtual Reality , Visitor Experience

Immersive Virtual Reality (IVR) has become increasingly important in cultural heritage applications. Recent advances, such as the integration of virtual agents and Artificial Intelligence (AI), have further reshaped the IVR landscape, paving the way for new applications with potential impact. Despite extensive research on their application, the user experience and usability of cultural content for end users remain largely overlooked. This study aims to conduct a preliminary analysis of an AI-powered virtual agent's impact on users in the context of cultural heritage. Participants could interact freely with the virtual agent, simulating a conversation about questions and curiosities as they would with an expert museum guide. A user study has been conducted, comparing two methods of information delivery in an IVR museum environment: a traditional explanatory panel and an AI virtual agent. Metrics collected were the time spent during each condition, the systems' overall user experience, and usability. The results suggest that virtual agents capture the user's attention more and encourage prolonged interaction due to novelty. However, the study also highlights the need to combine both methods to achieve optimal user engagement and usability.

Keywords: Artificial Intelligence , Cultural Heritage , Immersive Virtual Reality , User Experience , Virtual Agent

This work presents a succinct exploration of technological advancements in the field of Cultural Heritage preservation and restoration, as highlighted by the papers presented at the third Florence Heritech Conference, held in Florence (Italy) in 2022. In particular, it outlines the substantial impact of many technologies on several aspects of cultural heritage conservation including 3D scanning and 3D printing, artificial intelligence, multispectral imaging, nanotechnology-related technologies, and energy efficiency solutions. It aims to provide a bird-eye view of how digital preservation developments are changing the cultural heritage paradigm through scientific analysis and case studies. Accordingly, this work briefly hints at cutting-edge technologies used in Cultural Heritage to improve accessibility, support sustainable preservation techniques, and strengthen the legacy of cultural heritage for future generations.

Keywords: 3D printing , AI , cultural heritage , energy efficiency , imaging , nanotechnology

Perishable materials are strongly affected by climate changes that can seriously damage them. In this study, ancient wooden furniture inside the UNESCO site of the Reggia di Caserta has been surveyed to provide 3D volumes for structural analysis. Wooden objects are mostly affected by moisture and changing in the temperature during the year, most likely in a building that faces substantial changes between winter and summer. The process comprehended the combined use of photogrammetry and hand-held device to obtain accurate models. With this surveying pipeline, it was possible to scale the photogrammetric models and complete the missing parts. The process of the creation of volumetric models with the use of voxels have been analyzed to identify the problems and set a methodology for the use of these volumes in FEA software. The aim is to use the models for diagnostic studies for understanding the level of decay integrated with in situ thermographic surveys.

Keywords: 3D survey , FEM , Integration of data , Laser scanning , Photogrammetry , Structural analysis

Biofouling, the phenomenon involving the growth and accumulation of marine organisms on submerged surfaces, poses a significant challenge for the conservation of underwater structures and historical artifacts. Its presence can accelerate material degradation and complicate potential restoration efforts, especially in cases where direct recovery from the marine environment is not feasible. In this context, the early identification of biofouling is crucial for developing targeted intervention strategies and minimizing long-term damage. This study aims to lay the groundwork for creating a training dataset for a deep learning-based segmentation network. Images of submerged specimens were captured in both the visible spectrum and under UV illumination, which reveals biofouling often invisible to the naked eye. Using semi-automatic thresholding methods, segmentation masks were generated from UV images to approximate biofouling regions. RGB, HSV, Lab, and YCbCr color spaces were systematically compared to determine the most stable and reliable color model for segmentation. Results identified the HSV space as offering the most consistent thresholding performance across the dataset. These segmentation masks provide a foundation for training deep learning models aimed at automatically detecting biofouling in visible-light images, where manual annotation is challenging.

Keywords: Biofouling detection , Computer vision , Image segmentation , Underwater cultural heritage

Underwater robotic manipulation relies on visual feedback and experience, making precision challenging, especially in underwater cultural heritage (UCH). Errors in distance estimation risk collisions or improper grasping, endangering fragile artifacts. To overcome these challenges, operators should be equipped with advanced tools and sensors that enhance their perception and interaction, enabling more precise and controlled manipulation in complex underwater environments. To this end, the paper introduces a novel framework designed to improve environmental perception during underwater manipulation operations by integrating stereo vision and acoustic imaging sensors. Unlike traditional approaches, the proposed framework is applicable in both simulated and real-world environments, providing a versatile tool for underwater robotic applications. The core of the proposed framework consists of a simulation environment built on Unity and ROS2, replicating a system that includes a Remotely Operated Vehicle (ROV) equipped with a robotic manipulator, a stereo camera, and a forward-looking sonar. Preliminary results on stereovision and acoustic imaging simulations demonstrate how the integration of these sensing modalities improves environmental perception.

Keywords: Augmented reality , Marine robotics , Robot operating system , Underwater cultural heritage , Underwater manipulation

Monitoring marine environments is essential for understanding ecological dynamics and preserving underwater sites of scientific and cultural interest. While autonomous robotic systems can cover large areas and collect high-quality water data, scientific divers remain indispensable for survey operations due to their direct observations and selective sampling. However, underwater navigation presents significant challenges for researchers, including poor visibility, marine currents, and the absence of GNSS signals. To address these challenges, this study proposes the conceptual design of a motorized smart buoy capable of autonomous environmental monitoring and providing operational support to divers. The system integrates a suite of sensors for real-time measurement of physicochemical water parameters, a GNSS module for surface localization, and an acoustic positioning system to enhance underwater navigation. This system determines the diver's position by emitting and receiving acoustic signals. Once the position is calculated, the information is transmitted directly to the diver's tablet, enabling real-time awareness of their location, improving navigational safety, and allowing the collection of georeferenced data for more accurate environmental analysis. Furthermore, the implementation of Deep Reinforcement Learning (DRL) algorithms has been considered to optimize the trajectory of the smart buoy in dynamic marine environments, enhancing energy efficiency and monitoring accuracy. The proposed system represents a significant advancement in marine ecosystem monitoring, combining operational autonomy with adaptability to diverse application scenarios.

Keywords: Deep Reinforcement Learning (DRL) , Diver support , Marine monitoring , Smart buoy

This paper, in the frame of the Tectonic project (TEchnological Consortium TO develop sustaiNabIlity of underwater Cultural heritage), presents recent results obtained from the work on the shipwreck of the 19th Century schooner Emma, one of the selected submerged archaeological pilot sites. The wreck of Emma is located in Chubut province, Patagonia, Argentina. The main task consisted of the development of a 3D photogrammetric model to be integrated into a virtual reality (VR) end product. The technique employed in the process is described, noting the necessary adjustments required for its application in an underwater environment. Finally, the potential of this type of technique is discussed as a means of promoting tourism as well as underwater heritage management and protection, particularly important in the context of the characteristics of the remote Patagonian region.

Keywords: Patagonia , Photogrammetry , Shipwrecks , Underwater cultural heritage , Virtual reality

Italian hand gestures constitute a distinctive and widely recognized form of nonverbal communication, deeply embedded in everyday interaction and cultural identity. Despite their prominence, these gestures are rarely formalized or systematically taught, posing challenges for foreign speakers and visitors seeking to interpret their meaning and pragmatic use. Moreover, their ephemeral and embodied nature complicates traditional preservation and transmission approaches, positioning them within the broader domain of intangible cultural heritage. This paper introduces a machine learning–based framework for recognizing iconic Italian hand gestures, designed to support cultural learning and engagement among foreign speakers and visitors. The approach combines RGB–D sensing with depth-enhanced geometric feature extraction, employing interpretable classification models trained on a purpose-built dataset. The recognition system is integrated into a non-immersive virtual reality application simulating an interactive digital totem conceived for public arrival spaces, providing tutorial content, real-time gesture recognition, and immediate feedback within a playful and accessible learning environment. Three supervised machine learning pipelines were evaluated, and Random Forest achieved the best overall performance. Its integration with an Isolation Forest module was further considered for deployment, achieving a macro-averaged accuracy and F1-score of 0.82 under a 5-fold cross-validation protocol. An experimental user study was conducted with 25 subjects to evaluate the proposed interactive system in terms of usability, user engagement, and learning effectiveness, obtaining favorable results and demonstrating its potential as a practical tool for cultural education and intercultural communication.

Keywords: gesture recognition , human–computer interaction , intangible cultural heritage , Italian culture , machine learning , virtual reality

Bengala, a steamer that sank in 1889 near Capo Rizzuto, Italy, was a relatively new vessel for its time, with an unusually short 18-year service life, given that steamers of the period typically operated for 30 to 40 years. Despite its brief history, SS Bengala played a significant role in the development of Italy's young merchant navy, undergoing multiple ownership changes and serving various Italian shipping companies. Employed mainly along the route to Southeast Asia, it transported Italian migrants overseas and also participated in troop raids during the Italian military expedition to Eritrea in 1887. Despite its historical significance, no iconographic material has yet been found to depict SS Bengala, and archival research conducted in Italy and England has not uncovered any naval plans, photographs, or drawings of the ship. To overcome this gap, the authors employed new technologies and historical information to create a virtual reconstruction. This research combined archival sources with underwater surveys, including a detailed 3D survey by divers and archaeologists. Archival research, including consultation of official documents, provided critical information on the ship's dimensions, superstructure, rigging, materials, and construction methods. The 3D modelling of the ship's external hull, based on precise geometric data from the wreck site, offers a first step towards virtual reconstruction. The modelling is grounded in photogrammetric surveying techniques, ensuring high accuracy in the reconstruction process. The model can be used in augmented reality (AR) applications to enhance underwater exploration, allowing divers to visualise the reconstructed ship in its original environment. Additionally, it supports museum exhibits, interactive visualisations, and educational games, making it a valuable resource for engaging the public with maritime history and archaeology.

Keywords: 3D reconstruction , historic iron ship , maritime archaeology , shipwreck , steam-powered vessel and steamer , underwater heritage , underwater photogrammetry

Augmented Reality (AR) stands as a transformative technology reshaping the accessibility of cultural heritage (CH) sites and artworks in digital form. With the integration of virtual avatars, AR applications are poised to revolutionize visitor experiences by immersing them in interactive narratives. However, conventional AR systems often limit avatars to specific points of interest (POIs), lacking guidance throughout the exploration tour. This paper introduces an innovative AR-based system tailored for immersive CH encounters, leveraging virtual avatars as navigational aids through indoor and outdoor exhibits and artworks. The core of this system comprises two main components: an authoring tool for content creation and an AR application for user visualization and interaction. The authoring tool empowers creators to define POIs and seamlessly associate digital content, while the AR application enables visitors to engage with this content, guided by virtual avatars throughout the augmented tour.

Keywords: ARI questionnaire , Augmented reality , Cultural heritage , Virtual humans

The shape and tuning of bells provide helpful information about where the instrument was manufactured or located and the casting and tuning processes used. For this purpose, both shapes catalogues and methodologies for physical modelling and simulations of musical instruments' dynamical behaviour are presented in the literature. In several areas of the world, medieval or Renaissance bells are rare because of the remelting of the vast majority of specimens following fractures or breaks caused by wear and tear or traumatic events, such as earthquakes. As a result, the original geometric shape can only be reconstructed by analysing the relevant melting pots excavated by archaeological campaigns. Traditionally, such an analysis is carried out manually by archaeologists. The results are blurred by the difficulty in determining the axis of symmetry and the profiles of small fragments; furthermore, the fragments can rarely be reassembled on the fracture surfaces. To address these drawbacks, this research suggests a computer-based method for virtually reconstructing the bell shape from mantle fragments.

Keywords: 3D archeology , Automatic feature recognition , Cultural heritage , Medieval Bells

Underwater Cultural Heritage (UCH) sites offer unique opportunities for archaeological exploration and cultural tourism but remain difficult to interpret due to the environmental constraints of the underwater setting. This paper introduces an integrated Underwater Augmented Reality (UWAR) system designed to support real-Time, site-specific interpretation for recreational divers. The approach combines opto-Acoustic 3D reconstruction with thematic annotation and portable AR delivery. A high-resolution, georeferenced 3D model of the site is generated by fusing multibeam sonar and underwater photogrammetry data. This model provides the spatial framework for distributing interpretive content through georeferenced Points of Interest (POIs), including descriptive texts, images, and 3D reconstructions. The system architecture includes a smart buoy equipped with USBL and GNSS positioning systems and an underwater mobile device for AR visualization. This setup enables real-Time localization and contextual content delivery without the need for permanent infrastructure. The presented UWAR system aims to improve site readability, promote active learning and support sustainable cultural engagement, offering a scalable model for heritage interpretation in underwater environments.

Keywords: Smart Buoy , Underwater 3D Reconstruction , Underwater Augmented Reality (UWAR) , Underwater Cultural Heritage (UCH) , Underwater Navigation

Two iron objects, found during the excavation of a rural settlement in Ono San Pietro (Valle Camonica – Italy), dating back to the I-IV century CE, were interpreted as parts of a wagon wheel. A reverse engineering procedure was followed to support this hypothesis. The objects were digitalised by laser-scanning technique, to obtain virtual models that could be easily analysed and measured. Comparing the shape and the size of the objects with those of other finds of the Roman Age, the hypothesis that they were parts of a wheel appeared the most likely. In particular, one could be the external ring mounted at the hub ends; the other one could be a bushing to be mounted in the internal hub cavity to prevent wear of the wooden parts. Starting from the size of the finds, a possible wheel to which they could belong was reconstructed, taking as reference the proportions of some Roman wheels found elsewhere. Subsequently, the whole axle was reconstructed following the same concept. The load capacity of the axle was determined by means of Finite Element analyses, which revealed it was suitable for heavy load transportation.

Keywords: Finite Elements Analysis , Laser-Scanner Acquisition , Roman Age , Wagon , Wheel Parts

The use of virtual reality technologies in the field of cultural heritage can play a central role in enhancing visitors' experience and accessibility of artifacts and artworks. However, the virtual museum (VM), other than being captivating, should be inclusive, ensuring equal participation and learning opportunities for all people, including those with disabilities. Accordingly, the integration of visual stimuli with tactile information by means of haptic technology can provide an innovative medium to experience VM contexts, enhancing the quality visitors experience, especially with reference to people with vision impairments or blindness, according to a universal design perspective. Though haptic devices could represent an asset for cultural heritage fruition and education, only a limited number of studies considered their application to enhance the VM visitors' experience so far, while their suitability for people with vision impairments or blindness is far from being properly investigated. Therefore, this study aims at bridging this research gap, illustrating the methods and results of a co-design process of a VM application integrated with a haptic interface involving people with vision impairments or blindness. The developed application consists of a multi-modal system that integrates haptic feedback with audio and visual information, geared toward providing the most comprehensive and engaging experience possible for users with vision impairments or blindness.

Keywords: Accessibility , Cultural Heritage , Guidelines , Haptic Technology , Leisure , Virtual Reality Technologies , Visual Impairment , VM Applications

The shape and tuning of bells provide archaeologists with valuable insights into their historical origins and casting methods. Unfortunately, the availability of fully preserved medieval and Renaissance bells is limited worldwide due to the remelting of many specimens following fractures, wear, or traumatic events such as earthquakes. The original geometry is therefore reconstructed by archaeologists by examining uncovered external mould during excavations. However, determining the symmetry axis and interpreting the profiles of small fragments is not trivial, and fragments are not always easily reassembled along their fracture surfaces. To solve this issue, this paper presents a computer-based method that enables the automated virtual reconstruction of ancient bells from their external mould fragments. The approach performs geometric and differential analysis of discrete models obtained from 3D scans of the fragments, facilitating the retrieval of a consistent 3D shape, thereby aiding in the preservation and understanding of historical relics.