Track 04 – Acquisition and Digitization
Permanent URI for this collection
• Pedro Santos – Fraunhofer IDG, Germany • Martina Hoffmann – National Library of Switzerland, Switzerland • Fabio Remondino – FBK (Fondazione Bruno Kessler), Italy
Digitization and Technology
CultLab3D to CultArm3D - The first autonomous, robot-assisted, color-faithful 3D
digitization technologies for cultural heritage collections
] [
]
Pedro Santos, André Stork, and Dieter W. Fellner
Hacking Light in the Digitization of Archaeological Glass Vessels: the Quest for Geometric
Rigor
Vanessa Cornago Espuelas
A Practical Inverse Rendering Strategy for Enhanced Albedo Estimation for Cultural Heritage
Model Reconstruction
Ruggero Pintus, Antonio Zorcolo, Alberto Jaspe-Villanueva, and Enrico Gobbetti
Material Studies For Digital Heritage: Comparative Analysis of Geometric and Photometric 3D
Representations
Fabian Töpfer, Eliane Christ, Zhongyuan Yu, Lars Engeln, and Matthew McGinity
Evaluating the Impact of Lighting Conditions on Photogrammetric Acquisition of Cultural
Heritage
Federico Gangi, Malik Umair Shafqat, and Gabriele Guidi
Digitization Tools and Applications
Bringing Stones to Life: The First Digital 3D Library of Ancient Armenian Gravestones
Aleksei Andrianov, Garegin Muradyan, Zhanna Andrianova, and Narine Sarvazyan
Unsupervised Colorization and Diffusion-Based Virtual Try-On for Ottoman Heritage
Preservation
Zeynep Akant, Elman Ghazaei, and Selim Balcisoy
''Out There,'' Anywhere: Digital Proxies for Threatened Cultural Heritage Sites and
Structures
Eva Deisa, Sarah Tucker, Alex Kinnaman, and Todd Ogle
Level-of-Detail Digitization of High Ceilings in Virtual Reality
Jacob Edwards, Stephen D. Laycock, Thomas Roebuck, YingLiang Ma, and Cheng Wang
UAV survey and large-scale digitization. Avenues for making visible the massive data on the
archaeological landscape of the Lovo massif (DRC)
David Lo Buglio, Michel Lefèvre, Geoffroy Heimlich, and Clément Mambu Nsangathi
Drone-Based Magnetic Survey: Testing a New Approach for Archaeological Prospection
Alessia Mandorlo, Iacopo Nicolosi, Roberto Carluccio, Lorenzo Conti, Lorenzo Lambiase,
Samuele Fantini, Giancarlo Morelli, Giancarlo Pastura, Giuseppe Ceraudo, and Stefano Rl.
Campana
Comparing MVS and Gaussian Splatting for the 3D Reconstruction of Reflective and
Texture-less Cultural Heritage Artifacts
Paolo Clini, Roberto Pierdicca, Romina Nespeca, Renato Angeloni, and Laura Coppetta
Digitization and Segmentation
2D and 3D Semantic Segmentation for Interpreting and Understanding 3D Heritage Spaces
Ahmad El-Alailyi, Gabriele Mazzacca, Ashkan Alami, Nazanin Padkan, Narges Takhtkeshha,
Francesco Fassi, and Fabio Remondino
Comparing OCR Pipelines for Folkloristic Text Digitization
Octavian M. Machidon and Alina L. Machidon
Acquisition and digitization of large scale heritage scenes with open source project
https://github.com/MapsHD/HDMapping
Janusz Bedkowski, Marcin Matecki, Michal Pelka, Karol Majek, Tresya Fitri, and A. Kostrzewa
ArTLLaMA: Adaptating LLaMA to Performative Art Applications
Elisa Passone, Federico Borazio, Claudiu Daniel Hromei, Danilo Croce, and Roberto Basili
Towards interdisciplinary approaches combining AI and 2D/3D: Designing a digital
environment for the virtual reconstruction of a lost medieval church using a historical
ontology
Florent Laroche, Ambre Vilain, Mathis Vauxion, and Elouarn Le Chenadec
Digitization Case Studies
Sun Stones Chronicles: Enriching the Bornholms Museum Brightest Artifact Collection through
3D Scanning and Semantic Web Technologies
Nicola Lercari, M. Nicolás Caretta, Bruno Sartini, Yiming Du, Josephine Bergman, and Dario
Calderone
Virtual Reconstruction and Digital Twin of the Royal Monastery of San Benito of Sahagún: A
Strategy for the Documentation, Conservation, and Dissemination of Lost Heritage
David Marcos Gonzalez, Daniel López-Bragado, Jesús San José-Alonso, Juan José
Fernández-Martín, José Martínez-Rubio, and Antonio Alvaro-Tordesillas
Immersive RockArt: When rock carvings meet photogrammetry and computer graphics
Daniele De Luca, Maria Chiara Liguori, Antonella Guidazzoli, Elisa Mariarosaria Farella,
Fabio Remondino, Tiziana Cittadini, and Markus Loeffler
Spatial random access to explore heritage site using spherical video
El Mustapha Mouaddib, Guillaume Caron, and Arsalane Zarghili
Geometric Modeling for Immersive VR Exploration of Underground Heritage: Matera's Hypogeum
Case Study
Brigida Bonino, Daniela Cabiddu, Mattia D'Alonzo, Katia Lupinetti, Michela Mortara, and
Simone Pittaluga
3D Digitalization of Wooden Churches - Techniques and Challenges During Preservation
Efforts
Marcin Badurowicz, Stanislaw Piotr Skulimowski, Jerzy Montusiewicz, and Tomasz Szymczyk
Browse
Recent Submissions
Item UAV survey and large-scale digitization. Avenues for making visible the massive data on the archaeological landscape of the Lovo massif (DRC)(The Eurographics Association, 2025) Buglio, David Lo; Lefèvre, Michel; Heimlich, Geoffroy; Nsangathi, Clément Mambu; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe increasing power of digitisation tools and the democratisation of UAVs have encouraged the massive collection of data on a territorial scale [AbSL17]. While the need for digital documentation of cultural heritage and archaeological contexts on an unprecedented scale has continued to grow in recent years, so too has the need for methods to analyse and interpret the data collected [LoVa21]. By studying the archaeological landscape of the Lovo Massif (DRC) (Fig. 1), the aim of this research is to explore the methodological and technical methods that could help us to understand this territory. The nature of the sites studied, the difficulties of access or simply the size of certain archaeological areas have led in recent years to the emergence of survey methods able to extend examination beyond the 'visible' (Lidar survey, thermal survey, GPR). Behind the specific needs of archaeologists in terms of prospecting, one of the problems linked to the acquisition of large volumes of heterogeneous data lies in our ability to interpret them according to specific observation needs.Item A Practical Inverse Rendering Strategy for Enhanced Albedo Estimation for Cultural Heritage Model Reconstruction(The Eurographics Association, 2025) Pintus, Ruggero; Zorcolo, Antonio; Jaspe-Villanueva, Alberto; Gobbetti, Enrico; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioWe present a practical single-image framework to address uncontrolled global and local illumination effects in flash photography for improved albedo estimation and color projection onto 3D cultural heritage models. Our approach leverages an inverse rendering pipeline to process a single registered flash photograph and models ambient illumination due to environmental reflections and local interreflections. By compensating for direct and indirect light contributions, we recover a more reliable albedo signal for color projection onto the 3D model. We validate our method through extensive evaluations on two synthetic datasets and real-world acquisitions in conservation and museum settings, demonstrating its effectiveness in improving photometric accuracy and support for relighting, and proper integration of optimized color data into existing 3D models.Item Acquisition and digitization of large scale heritage scenes with open source project https://github.com/MapsHD/HDMapping(The Eurographics Association, 2025) Bedkowski, Janusz; Matecki, Marcin; Pelka, Michal; Majek, Karol; Fitri, Tresya; Kostrzewa, A.; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThis paper describes an open source project https://github.com/MapsHD/HDMapping for large-scale 3D mapping using an open-hardware hand-held LiDAR measurement device available at https://github.com/JanuszBedkowski/mandeye_controller in application of large-scale heritage scenes acquisition and digitization. It implements multi view terrestrial laser scanning algorithms, LiDAR odometry, Pose Graph SLAM (Simultaneous Localisation and Mapping), NDT (Normal Distributions Transform) and ICP (Iterative Closest Point). Mobile mapping systems is based on LiVOX MID360 - laser scanner with non repetitive scanning pattern equipped with equirectangular camera. This project runs from 2023, the current version v0.76 has significant improvements in lidar odometry and georeferencing. The goal of the project is to provide an affordable mobile mapping system and an open source software that can be widely used also by Culture Heritage community.Item 2D and 3D Semantic Segmentation for Interpreting and Understanding 3D Heritage Spaces(The Eurographics Association, 2025) El-Alailyi, Ahmad; Mazzacca, Gabriele; Alami, Ashkan; Padkan, Nazanin; Takhtkeshha, Narges; Fassi, Francesco; Remondino, Fabio; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe 3D digitization of Cultural Heritage (CH) sites has become increasingly requested for documentation, preservation, and analysis applications. Beyond capturing 3D spatial geometry, the semantic interpretation and understanding of digital models are critical for enabling meaningful CH studies and facilitating informed conservation strategies. However, manual annotation and classification of architectural elements and surface pathologies remain labor-intensive and time-consuming, underscoring the need for automated approaches. This study presents a comparative analysis between two distinct semantic segmentation frameworks: (1) a 2D-to-3D pipeline that projects 2D image-based detections onto 3D point clouds produced with V-SLAM data and (2) direct segmentation methods of 3D point clouds acquired with portable LiDAR sensors. These frameworks are evaluated on data acquired using two distinct mobile mapping systems (MMS): (1) a fisheye multi-camera Visual SLAM-based portable system (ATOM-ANT3D) for the 2D-to-3D pipeline; (2) a LiDAR-based MMS (Heron MS Twin Color) for the 3D segmentation methods. Achieved results demonstrate the ability of the proposed frameworks to generate semantically enriched 3D heritage data, with the 2D-to-3D method slightly outperforming the 3D segmentation techniques.Item Material Studies For Digital Heritage: Comparative Analysis of Geometric and Photometric 3D Representations(The Eurographics Association, 2025) Töpfer, Fabian; Christ, Eliane; Yu, Zhongyuan; Engeln, Lars; McGinity, Matthew; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio3D digitisation offers unique opportunities for research, preservation, distribution, presentation, and contextualisation of artefacts in museum and heritage contexts. However, despite advances in the field, no single contemporary capture method or representation can perfectly capture all artefacts for all purposes. For example, heterogenous materials, transparent surfaces, intricate structures, motion, and interactivity all remain significant challenges for contemporary 3D digitisation techniques. From the perspective of digital heritage, we present here an analysis of two prominent techniques: ''structure from motion'' surface-based ''geometric'' representations and surface-free ''photometric'' Gaussian Splat representations. We discuss the advantages and disadvantages of both with respect to digitisation workflows, usability, integrability, and practicality in museum contexts, with a particular focus on performative artefacts, and propose a goal-oriented guide for digital heritage professionals embarking on digitisation projects.Item 3D Digitalization of Wooden Churches - Techniques and Challenges During Preservation Efforts(The Eurographics Association, 2025) Badurowicz, Marcin; Skulimowski, Stanislaw Piotr; Montusiewicz, Jerzy; Szymczyk, Tomasz; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioIn this paper, the authors are showing the organizational and technical challenged encountered while preserving wooden architecture in the Carpathian region. The authors are presenting two case studies of 3D scanning of wooden churches in Romania and Poland, which were performed using terrestrial laser scanning (TLS) and terrestrial short-range photogrammetry (TSRP). The paper describes the workflow of the operation, challenges during scanning due to both organization, technology limitations, access to the buildings and even weather, and solutions applied during the process of digitalization of these historical buildings.Item Immersive RockArt: When rock carvings meet photogrammetry and computer graphics(The Eurographics Association, 2025) Luca, Daniele De; Liguori, Maria Chiara; Guidazzoli, Antonella; Farella, Elisa Mariarosaria; Remondino, Fabio; Cittadini, Tiziana; Loeffler, Markus; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioRock Art Immersive is an interdisciplinary project for the 3D documentation, valorisation, communication, and tourist promotion of the UNESCO site of the Pitoti rock carvings in Val Camonica (Italy). Photogrammetry and Computer Graphics are coupled to create reality-based interactive and communicative material to safeguard and valorize a heritage site.Item Hacking Light in the Digitization of Archaeological Glass Vessels: the Quest for Geometric Rigor(The Eurographics Association, 2025) Espuelas, Vanessa Cornago; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe 3D digitization of heritage has revolutionized archaeological research and the dissemination of archaeological materiality. Emerging new technologies not only allow to analyze data from new perspectives and dimensions, in a literal sense; but have also democratized access to material culture and enriched the public's experience of history. However, a significant lacuna exists in virtual collections and databases: glass objects. In both virtual museum expositions and archaeological research, ancient glass tableware is often largely forgotten. In museums, glass artifacts are often confined to display cases. In archaeological research, ancient glass is a subject that has received comparatively little scholarly attention, and the literature on its craftmanship is scant when compared to that of its functional counterparts in other materials. Fragile, fragmentary and poorly studied, ancient glassware current status can be attributed, in part, to the technical challenges posed by the 3D digitization of glass artifacts. In this way, the new computational tools for analysing archaeological data cannot access these types of productions because they are not available in a digital version. The inherent nature of glass presents significant difficulties for digitization techniques, as the optical properties of reflectance, reflexivity, and transparency prevent its surfaces from being read by any light-based method. Glass exhibits complex and diverse light-redirecting and -absorbing characteristics. Consequently, various 3D scanning and photogrammetry techniques encounter problems in geometrically capturing glass objects. The present study aims to overcome the difficulties of 3D glass acquisition by proposing the use of a new methodology based on photogrammetry, which enables the digitization of the geometry of these elusive pieces with rigor. This technique has been specifically designed to capture light at its optimal deflection in glass vessel surfaces and to record it as reliable image data in order to build geometrically accurate 3D models. Thus, this paper intends to tackle the 3D acquisition of the archaeological glass objects even beyond the renders; that is: data has been collected and processed in a hermetic and thorough polygonal mesh that can be texturized and optimized afterward. The methodology has been implemented in the analysis of Roman glassware. The resulting precise meshes make it a technique that can be applied to any computational morphometric analysis on any type of archaeological glass artifacts, in addition to completing the digital heritage collections.Item Comparing OCR Pipelines for Folkloristic Text Digitization(The Eurographics Association, 2025) Machidon, Octavian M.; Machidon, Alina L.; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR) approaches for Slovene folkloristic and historical text digitization, integrating both traditional methods and large language models (LLMs) to improve text transcription accuracy while maintaining linguistic and structural integrity. We compare single-stage OCR techniques with multi-stage pipelines that incorporate machine learning-driven post-processing for text normalization and layout reconstruction. While LLM-enhanced methods show promise in refining recognition outputs and improving readability, they also introduce challenges related to unintended modifications, particularly in the preservation of dialectal expressions and historical structures. Our findings provide insights into selecting optimal digitization strategies for large-scale folklore archives and outline recommendations for developing robust OCR pipelines that balance automation with the need for textual authenticity in digital humanities research.Item ArTLLaMA: Adaptating LLaMA to Performative Art Applications(The Eurographics Association, 2025) Passone, Elisa; Borazio, Federico; Hromei, Claudiu Daniel; Croce, Danilo; Basili, Roberto; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioPerformative Arts represent a compelling and underexplored domain for the application of Generative AI, given their rich conceptual complexity and cultural depth. This paper presents ArTLLaMA, a domain-adapted version of the LLaMA language model, designed to support natural language querying of ArTBase, the first national database of Italian theatres and theatre archives. We focus on the Text-to-SQL task: automatically translating user questions into executable SQL queries. Off-the-shelf models often fail in this setting due to a lack of domain knowledge and schema awareness. To bridge this gap, we propose a two-stage fine-tuning methodology: first, we train the model to internalize the Entity-Relationship (ER) schema of ArTBase; then, we fine-tune it on a curated set of over 800 natural language-SQL query pairs reflecting real use cases in the domain. Our results show that schema-informed fine-tuning significantly boosts accuracy, with the best model achieving over 70% exact match andgenerating correct SQL even for complex queries involving multi-table joins and aggregations. Compared to general purpose models like ChatGPT, our approach yields more accurate, schema-compliant outputs. Beyond technical improvements, this work underscores the value of interdisciplinary collaboration: by embedding domain knowledge from the humanities into AI systems, we enable new forms of access, interaction, and understanding of cultural heritage data.Item Evaluating the Impact of Lighting Conditions on Photogrammetric Acquisition of Cultural Heritage(The Eurographics Association, 2025) Gangi, Federico; Shafqat, Malik Umair; Guidi, Gabriele; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioAccurate documentation of cultural heritage artifacts is essential for study, conservation, and exhibition. While optimal lighting is known to minimize photogrammetric uncertainty, the quantitative impact of progressively deteriorating illumination, when compensated by ISO adjustments, remains underexplored. This study experimentally evaluates how varying ISO levels affect the geometric accuracy of dense 3D point clouds generated through Structure from Motion / Image Matching (SfM/IM). A sandstone sample, previously digitized with a high accuracy structured light scanner, served as the reference model. Three cameras of different generations were tested in a controlled darkroom, with lighting progressively reduced and exposure adjusted to maintain correct image brightness. Results reveal an unexpectedly stable measurement uncertainty across a wide ISO range (ISO 100-51,200 for the Sony α7R IV, ISO 100-6,400 for the Nikon D810, and ISO 100- 3,200 for the Canon EOS 4000D), followed by a sharp accuracy drop at the highest ISO setting of each device. While geometric accuracy remained largely unaffected within these ranges, tie point counts decreased and reprojection errors increased steadily with ISO, indicating a gradual loss of feature robustness. These findings show that modern sensors can sustain high-accuracy photogrammetry far beyond traditionally accepted ISO limits, offering practical tolerance thresholds for reliable heritage documentation under challenging lighting conditions.Item Comparing MVS and Gaussian Splatting for the 3D Reconstruction of Reflective and Texture-less Cultural Heritage Artifacts(The Eurographics Association, 2025) Clini, Paolo; Pierdicca, Roberto; Nespeca, Romina; Angeloni, Renato; Coppetta, Laura; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThis study presents a comparative analysis of Multi-View Stereo (MVS) and 3D Gaussian Splatting (GS) for the three-dimensional reconstruction of cultural heritage artifacts characterized by reflective and texture-less surfaces, conditions that traditionally challenge image-based modeling techniques. Two case studies, a ceramic and a bronze head, were documented through controlled photographic acquisition and processed using both methods. Laser scanning served as a geometric benchmark for quantitative evaluation. Results demonstrate that GS provides more spatially homogeneous reconstructions and enhanced visual coherence, particularly in regions affected by specular highlights and low surface texture. Visual comparisons further highlight the potential of GS to deliver smooth, photorealistic renderings through its volumetric, view-dependent representation.Item CultLab3D to CultArm3D - The first autonomous, robot-assisted, color-faithful 3D digitization technologies for cultural heritage collections(The Eurographics Association, 2025) Santos, Pedro; Stork, André; Fellner, Dieter W.; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe European Cultural Heritage Strategy for the 21st century has spurred demand for fast and efficient 3D digitization technologies for cultural heritage artifacts. Unlike widely automated 2D digitization, 3D often required significant manual intervention. This is no longer the case. Our pioneering efforts have made large scale 3d digitization easy-to-use, fast and economic, as well as robust and reliable. In 2012 at the Fraunhofer Institute for Computer Graphics Research IGD the Department for Cultural Heritage Digitization was created and entrusted with the mission to develop the first reference system for autonomous 3D digitization. Its first project was CultLab3D funded by the German Federal Ministry of Economy and Energy affairs. A very early version of the CultLab3D digitization pipeline was then presented at the first Digital Heritage conference in Marseille in 2013 winning the technical proficiency award. In 2018 we were recognized with the EU Prize for Cultural Heritage / Europa Nostra Award. In due course of our research and after many lessons learned evaluating our technologies with numerous cultural heritage institutions worldwide, we have constantly improved and refined them. As a result, in 2023/2024 we created a spinoff company Verus Digital GmbH which now commercializes the CultArm3D technology and offers 3d digitization services to cultural heritage institutions. In addition, we also successfully managed to perform technology transfer to other domains benefiting from autonomous 3d digitization of arbitrary objects, such as the dismantlement of nuclear powerplants resulting in the first autonomous ultrahigh-pressure waterjet decontamination system operational since 2024 at RWE Nuclear GmbH in Biblis, Germany and awarded the EU Innovation Prize on Nuclear Waste Management 2022. Our paper provides an overview of the challenges and developments from the first autonomous, robotassisted 3D digitization technologies to their current state (see Figure 1), ensuring completeness and repeatable high quality of resulting 3D models for objects of arbitrary shapes and a wide range of materials, as well as the automated generation of by-products such as decimated web, AR, 3D print models or rendered videos. We conclude with a discussion of current and future lines of research to further improve the capabilities of the CultArm3D platform.Item Spatial random access to explore heritage site using spherical video(The Eurographics Association, 2025) Mouaddib, El Mustapha; Caron, Guillaume; Zarghili, Arsalane; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioSpherical images are particularly adapted to develop virtual tours of heritage monuments. While Lidar scanning, photogram- metry and rotating camera systems can lead to produce spherical images, compact dual-fisheye cameras are accurate enough for many uses, such as virtual tour, and easy to use by a non-expert. But the classical software consider placing a few im- ages manually on the blueprint of the environment. Then, the user navigation in the virtual monument is limited to generated transitions between a few locations. Instead of a few pictures, this paper considers a spherical video recorded while walking within a monument and illustrates how to explore spatial dimensions of the environment where the video was taken, beyond the time scroll-bar. To this end, spherical visual Simultaneous Localization And Mapping (SLAM) and the alignment of the resulting map to an architectural blueprint are combined to create a spatio-temporal virtual tour from a video. The concept is demonstrated on the al-Qarawiyyin Mosque in Fez, Morocco, with access to the virtual tour interface at this link: https://home.mis.u-picardie.fr/~ecathedrale/alQarawiyyin/.Item Towards interdisciplinary approaches combining AI and 2D/3D: Designing a digital environment for the virtual reconstruction of a lost medieval church using a historical ontology(The Eurographics Association, 2025) Laroche, Florent; Vilain, Ambre; Vauxion, Mathis; Chenadec, Elouarn Le; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThis article explores the intersection of artificial intelligence (AI), 3D modeling, and historical ontology in the context of digital heritage. It presents an interdisciplinary methodology designed to enhance the accuracy and epistemological transparency of virtual reconstructions, using the lost Cordeliers Church of Nantes as a case study. Generative AI models, supported by curated databases and structured ontologies (OMeKA-S), are used to produce historically grounded visual hypotheses. The process includes source verification, bias analysis, and an iterative evaluation protocol by domain experts. The study also examines the ethical and methodological implications of using AI in the humanities, advocating for transparent, explainable, and human-centered AI workflows. By combining technical innovation with heritage expertise, this work offers a reproducible framework for digital museography and future research in the digital humanities.Item Unsupervised Colorization and Diffusion-Based Virtual Try-On for Ottoman Heritage Preservation(The Eurographics Association, 2025) Akant, Zeynep; Ghazaei, Elman; Balcisoy, Selim; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioColorizing historical images and modernizing traditional attire are key to bridging past and present in digital heritage preservation. Accurate colorization improves the interpretation of old photos, while modernizing historical attire supports cultural adaptation and fashion preservation. This paper presents an unsupervised method for colorizing 19th century images using GANs, trained with a dataset from modern-historical films. By leveraging the GAN discriminator, realistic colorizations are generated without paired data, capturing the textures and authenticity of historical scenes. A diverse film-based dataset enables the model to generalize across eras. Additionally, historical clothing is segmented and transferred onto modern subjects using diffusion-based virtual try-on techniques. Together, these methods support cultural preservation by blending historical accuracy with modern representation.Item ''Out There,'' Anywhere: Digital Proxies for Threatened Cultural Heritage Sites and Structures(The Eurographics Association, 2025) Deisa, Eva; Tucker, Sarah; Kinnaman, Alex; Ogle, Todd; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioCultural heritage sites and structures located in remote environments or composed of fragile materials face numerous threats from degradation, inaccessibility, and lack of preservation support. This paper introduces an in-progress multimodal digitization project for a remote sculpture trail, an open-air art installation composed of wooden sculptures, in southwest Virginia. This project combines photogrammetry, Gaussian splatting, LiDAR, volumetric capture, and oral history to create an immersive digital proxy of the site and experience. It proposes a replicable, scalable model for capturing and preserving complex cultural heritage assets, leveraging interdisciplinary expertise and prioritizing cross-departmental collaboration and digital preservation strategies for XR content. This paper presents the comprehensive project plan, details current progress, and discusses ongoing planning considerations.Item Level-of-Detail Digitization of High Ceilings in Virtual Reality(The Eurographics Association, 2025) Edwards, Jacob; Laycock, Stephen D.; Roebuck, Thomas; Ma, YingLiang; Wang, Cheng; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe digitization of elevated ceilings featuring intricate 3D patterns in heritage settings presents significant challenges due to their substantial height and constrained accessibility. To address this, we propose a hybrid Level of Detail (LOD) framework that synergizes 3D Gaussian Splatting (3DGS) for rapid base reconstruction with targeted 3D scanning of regions of interest (ROIs). First, 3DGS is used to rapidly generate a low-LOD, real-time navigable model of the entire ceiling. Second, accurate 3D scanning of selected ROI captures fine surface details. This two-stage workflow significantly reduces processing time compared to full-structure scanning while preserving spatial context, enabling seamless transitions between broad-scale exploration and immersive inspection of high-fidelity fragments. Validated through a case study at the National Trust's Blickling Hall, a 17th-century gallery with a 37.5-meter-long and 4.8-meter-high ceiling, our method demonstrates scalable potential for heritage conservation, offering a blueprint for balancing reconstruction efficiency with immersive engagement.Item Bringing Stones to Life: The First Digital 3D Library of Ancient Armenian Gravestones(The Eurographics Association, 2025) Andrianov, Aleksei; Muradyan, Garegin; Andrianova, Zhanna; Sarvazyan, Narine; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioWe report the creation of a high-resolution 3D digital libraries of khachkars and tapanakars, ornately carved gravestones that offer a rare glimpse into the daily lives of ordinary Armenians during the Middle Ages. Khachkars are vertical stelae bearing ornate crosses and geometric motifs, while tapanakars feature a pyramidal form adorned with various everyday scenes such as horseback riding, dancing, trading, and communal feasting. Centuries of physical and environmental stress have threatened these carvings and no 3D digital records of them currently exist. Using photogrammetry and LiDAR scanning technologies, we have created fully rotatable 3D digital twins of over 70 tapanakars and 150 khachkars with the millimeter-level precision. These models capture the intricate carvings and iconography that traditional photography often misses, especially on weathered or lichen-covered surfaces. We also developed image processing steps to help convert barely visible carvings into their linear outlines enabling future epigraphic interpretation and the use of machine learning algorithms. Two dedicated websites have been created to make these 3D libraries publicly accessible and to allow scholars, students, and enthusiasts worldwide to explore their cultural and artistic significance across different interdisciplinary projects. These unique collections offer a valuable dataset for image processing and computer vision studies, such as pattern recognition, feature extraction, and 3D modeling techniques. Beyond academic use, this resource has potential applications in education, virtual exhibitions, and cultural tourism promoting Armenian cultural heritage on an international scale.Item Virtual Reconstruction and Digital Twin of the Royal Monastery of San Benito of Sahagún: A Strategy for the Documentation, Conservation, and Dissemination of Lost Heritage(The Eurographics Association, 2025) Gonzalez, David Marcos; López-Bragado, Daniel; José-Alonso, Jesús San; Fernández-Martín, Juan José; Martínez-Rubio, José; Alvaro-Tordesillas, Antonio; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThe virtual reconstruction of lost heritage ensembles has become an essential tool for the research, conservation, and dissemination of cultural heritage. This paper presents the application of advanced digital methodologies-terrestrial and aerial photogrammetry, 3D laser scanning, and 3D modeling using Blender-to the Royal Monastery of San Benito of Sahagún (León, Spain), one of the principal centers of Cluniac monasticism on the Iberian Peninsula. Through an interdisciplinary approach, a rigorous digital model has been developed that integrates historical, documentary, and geometric sources, enabling a substantiated restitution of the architectural configuration of the complex. The results highlight the potential of digital technologies not only for the restitution of lost volumetric structures but also as a basis for preventive conservation strategies, academic research, and the creation of immersive experiences aimed at both specialist and general audiences, thereby contributing significantly to the heritage valorization of the site.Item Sun Stones Chronicles: Enriching the Bornholms Museum Brightest Artifact Collection through 3D Scanning and Semantic Web Technologies(The Eurographics Association, 2025) Lercari, Nicola; Caretta, M. Nicolás; Sartini, Bruno; Du, Yiming; Bergman, Josephine; Calderone, Dario; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioGalleries, libraries, archives, and museums increasingly rely on 3D digitization, web visualization, and 3D printing to document, analyze, and share cultural artifacts in novel ways that ensure digital preservation and engage visitors. This paper showcases how handheld structured-light 3D scanning, WebGL visualization, and semantic web technologies have been leveraged to digitize and enhance access to Denmark's cultural heritage, focusing on the Bornholms Museum collection. We have developed a streamlined digitization workflow that produces highly detailed digital twins of Neolithic artifacts from the sites of Vasagård and nearby Rispebjerg, archiving them in ways compatible with the Danish national database for archaeological heritage while utilizing the latest data curation and dissemination techniques and standards, such as WebGL visualization and FAIR principles. The significance of exploring the rich archaeological materials found at these sites located on the island of Bornholm, Denmark, lies in the fact that digitization and digital exploration enhance our understanding of the types and histories of interactions among different groups and farming communities in the Baltic, including their technology, religion, and social organization. By enriching the digital twins with symbolic and cultural interpretations and structuring data using the CIDOC Conceptual Reference Model and the ICON Ontology, our results demonstrate how to successfully integrate 3D heritage datasets with other global heritage resources. This expands access to Denmark's ancient history and allows the Bornholms Museum to reach new audiences both locally and internationally.Item Geometric Modeling for Immersive VR Exploration of Underground Heritage: Matera's Hypogeum Case Study(The Eurographics Association, 2025) Bonino, Brigida; Cabiddu, Daniela; D'Alonzo, Mattia; Lupinetti, Katia; Mortara, Michela; Pittaluga, Simone; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioThis paper present a methodology for reconstructing and optimizing 3D digital models of complex, tangible underground heritage sites that are difficult to access or even closed to the public, with the ultimate goal of integrating them into interactive virtual reality experiences, both for preservation and to make them accessible to a wider audience. The approach is demonstrated through the complete digitization of Matera's Hypogeum, in southern Italy. Faced with the site's challenging conditions (i.e., intricate passageways, poor lighting, and physical constraints), we developed a specialized workflow that combines handheld laser scanning acquisition with optimized mesh processing, in order to produce a model that can balance details visualization and realism with performance efficiency when used in VR environments. A preliminary development of an immersive VR application is also presented to provide an initial qualitative analysis of the model.Item Drone-Based Magnetic Survey: Testing a New Approach for Archaeological Prospection(The Eurographics Association, 2025) Mandorlo, Alessia; Nicolosi, Iacopo; Carluccio, Roberto; Conti, Lorenzo; Lambiase, Lorenzo; Fantini, Samuele; Morelli, Giancarlo; Pastura, Giancarlo; Ceraudo, Giuseppe; Campana, Stefano Rl.; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, FabioIn recent times, drones equipped with a variety of sensors, such as multispectral, thermal, and LiDAR, have been increasingly used in various archaeological tasks. There is also a growing interest in using geophysical sensors, like magnetometry (MAG), on Unmanned Aerial Vehicles (UAVs). One of the key challenges is selecting the most suitable and effective systems for archaeological purposes. Succinctly, this paper aims to assess the inner workflow established of Drone-based MAG system and briefly highlight its advantages and limitations in the archaeology field. Instead of discussing specific market-available systems, this essay provides a comprehensive overview of Drone-based MAG applications.