Track 05 – Analysis and Interpretation

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607222

Browse

Now showing 1 - 20 of 28

4D Data Organization and Alignment atWorld Scale
(The Eurographics Association, 2025) Münster, Sander; Bruschke, Jonas; Komorowicz, Dávid; Preßler, Rebecca Debora; Rajan, Vaibhav; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
A current challenge related to 4D viewers at world scale is the low number and geographic and temporal coverage of 3D models available. To overcome this issue, we work on different tools to (1) harvest 3D models, images, and location-based information from multiple sources via automated and community-based approaches; (2) automatically process these into 4D cityscape models; (3) make the 4D models accessible in two visualizations: via a 4D browser and a location-dependent augmented reality representation. Since previous articles report on the pipeline, tools, and usage scenarios, this contribution highlights ongoing developments in (1) large-scale 3D data retrieval; (2) 3D mesh model and LiDAR processing; and (3) novel view synthesis via Gaussian Splatting. The datasets are viewed in two 4D world viewers for (4) desktop browsing and (5) location-based mobile use. To date, they have been tested in seven countries.
Acting Like an Expert: Analyzing Eye and Movement Behavior when Exploring Archaeological Artifacts
(The Eurographics Association, 2025) Dumonteil, Maxime; Nicolas, Théophane; Macé, Marc J.-M.; Gouranton, Valérie; Leguedois, Yan; Gaugne, Ronan; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
This study proposes a novel methodological framework for investigating the visual exploration of archaeological artifacts in both real and virtual environments, integrating eye-tracking and movement data to analyze user behavior. Focused on three vases of varying shapes and decorative registers, the research examines the influence of object characteristics and user expertise on exploration strategies. Our results reveal that while both expert and non-expert participants identify structural and diagnostic features, such as geometric patterns and manufacturing traces, experts engage in more integrative, analytical exploration, focusing on both technical and decorative aspects. In contrast, non-experts prioritize prominent visual cues, often without full comprehension of their significance. These findings demonstrate that visual behaviors are influenced both by the physical characteristics of the artifacts and by the observer's level of expertise. They also show that certain visual cues--such as shape transitions or manufacturing marks--are particularly effective in triggering recognition, even among non-experts. This study contributes to neuro-archaeology by advancing eye-tracking and users' movements analysis as tools for analyzing cognitive processes in archaeological interpretation, offering a robust, reproducible methodology that can be applied to diverse archaeological contexts, enhancing our understanding of how artifacts reveal archaeologically meaningful information through visual perception.
Advancing Armenian Inscription Recognition
(The Eurographics Association, 2025) Nersesian, Gevorg; Sarvazyan, Narine; Khachatryan, Suren; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Armenian monuments are rich in carved stone inscriptions. These inscriptions serve as vital records of cultural and linguistic heritage, offering insights into the lives, beliefs, and traditions of Armenians during the Middle ages. However, detecting and comprehending these inscriptions pose significant challenges. Due to weathering, vandalism, erosion, and the complexity of ancient scripts, many of these texts remain unreadable. Yet, the few existing studies indicate that deciphering these messages from the past is feasible with technological advancements. In the present project we study a unique, newly created and unex- plored collection of digital twins of Armenian tapanakars (tombstones) and khachkars (cross-stones) focusing on hierarchical segmentation of the images using the detected geometrical and statistical features. The results are applied to character classi- fication and the accuracy of the generated images is estimated. Since the detection stage of the algorithm is universal for any kind of shapes, it opens up new research avenues that extend beyond text recognition alone. The same pipeline can be adapted to identify decorative motifs, geometric symbols, and other visual patterns commonly found on tapanakar surfaces.
Building Height Assessment for Heritage Site's Surroundings using 3D-GIS Multiple Scenarios
(The Eurographics Association, 2025) Sukwai, Janjira; Srinurak, Nattasit; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
A heritage property associated with a wider setting of natural landscape necessitates specific approach to safeguarding the values and integrity it carries. This study proposed conservation and management practices to look into height intrusion that may have had an adverse visual impact on a heritage site's surroundings both in the immediate vicinity and the extend beyond to its wider setting. A heritage site - Suan Dok Temple in Chiang Mai city, Thailand, was selected as a case study using the Viewshed analysis to investigate visibility of the temple with two distinct heights of stupas: Suan Dok height and Average height, as well as its associated mountain landscape as a result of building height impact in the adjacent, close, and mountain view zones. And later to comparing scenarios created by Computer Generative Architecture (CGA) to estimate optimal or critical building height for each view zone. The results indicated that, in the adjacent zone, the most critical building height range is less than 15 and 9 meters, respectively. Further from the heritage site, in the close zone, the critical building height range is less than 21 and 15 meters, respectively. The mountain backdrop naturally exhibits a direct variation based on the height of the taller buildings, necessitating further discussion of the optimal or critical height. The building height scenario presented in this study demonstrates the potential of employing 3D GIS through the rule package in CGA to assess the height of buildings within the heritage site's surrounding area. This approach presents an opportunity to evaluate the building height regulations in the context of urban planning and design, particularly regarding the preservation of the heritage's visual integrity.
Creative Processes of the Visual Arts and Generative AI. Correspondences between Michelangelo and Sebastiano Del Piombo in the Flagellation of Christ Ideation
(The Eurographics Association, 2025) Barbieri, Costanza; Clini, Paolo; Quattrini, Ramona; Pieruccini, Paolo; D'Alessio, Mirco; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Is it possible to visualize the creative process of the art in the making? How can we display an intangible phenomenon such as artistic research to make it perceivable and knowable? In the Enacting Artistic Research (EAR) project, a series of examples were identified for the choice of a case study that could lend itself to the continuous representation of the creative process. The choice fell on Michelangelo's preparatory drawings for the Flagellation of Christ for the Borgherini Chapel in San Pietro in Montorio, which Sebastiano del Piombo would have completed between 1516 and 1522, followed by other studies and other drawings for the Altarpiece of the Flagellation for the Church of Santa Maria del Paradiso in Viterbo in 1525. This series of drawings is particularly significant because it allows us to follow the changes made from the first idea, or first thought, through the study drawings or cartoons, up to the final phase of the underdrawing which can be read in infrared reflectography under the painting and then in relation to the chosen pictorial solution. It emerges, from this sequence, that Sebastiano lengthens the figure of Christ and rotates his face to accentuate pathos, involving the observer more closely. In order to enhance the creative process, the paper will present a workflow for the analysis, knowledge creation and storytelling of the artistic process, based on Gigapixel images, Artificial Intelligence generative tools and Large Language Models. The idea is to validate previous analysis thanks to the digital approach and to assess new forms of narratives, effectively exploiting the high-quality facsimile as well as the various AI technologies.The pilot case introduces innovative investigative and visual restitution techniques, such as virtual reality (VR), extended reality (XR), advanced imaging, and 3D modeling. Through the collaboration of scientists, 3D experts, and art historians, this groundbreaking approach unveils artistic research within creative processes, opening new avenues of aesthetic understanding.
Digital Exploration of the Hydrosystems of the Haut Adour (French Pyrenees)
(The Eurographics Association, 2025) Gherdevich, Davide; Costa, Laurent; Mermet, Eric; Cerbelaud, Fabien; Desplain, Aurelia; Sabatier, Richard; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
This research focuses on identifying hydrosystems in the Haut-Adour region of the Pyrenees (France), including lakes, streams, canals, and ancient water infrastructure. These elements reveal long-term human and animal use of the mountain landscape, shaped by cycles of occupation and abandonment. Using digital tools like IGN orthophotos and high-resolution LiDAR, the team developed a method to map and analyze these systems. Fieldwork, drone imagery, and 3D scanning further supported the study, which highlights the evolving relationship between societies and their environment in the face of social and climate change.
Enhancing Cultural Heritage with Generative AI: A Comparative Framework for the Evaluation of 3D Model Accuracy and Visual Fidelity
(The Eurographics Association, 2025) Balloni, Emanuele; Paolanti, Marina; Uggeri, Jacopo; Zingaretti, Primo; Pierdicca, Roberto; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
The digitization of Cultural Heritage (CH) has become a vital tool for preservation and dissemination, with 3D reconstruction playing a key role in capturing intricate geometries and visual details of artifacts. While traditional methods like photogrammetry and laser scanning are effective, they often involve labor-intensive processes and struggle with complex material properties. Recent advancements in Generative AI (GenAI), particularly Large Reconstruction Models (LRMs) such as TRELLIS, offer promising alternatives for 3D generation. However, their application in CH remains underexplored. This paper introduces a novel comparative framework to evaluate the accuracy and visual fidelity of 3D GenAI models in the CH domain. Focusing on TRELLIS, the framework assesses single-view and multi-view 3D generation across five diverse CH scenes, employing both 2D (PSNR, SSIM, LPIPS) and 3D (Chamfer Distance, F-score, Accuracy) metrics. Results demonstrate superior performance for individual artifacts (e.g., Minareto, Greek Vase) compared to complex architectural scenes, with multi-view generation consistently outperforming single-view approaches. The study highlights the potential of GenAI for CH preservation while identifying challenges in large-scale reconstructions, paving the way for future hybrid methodologies and sparse-view optimizations.
From Scanned Pages to Semantic Graphs: Scalable Methods for Extracting Historical and Cultural Knowledge Across Heterogeneous Texts
(The Eurographics Association, 2025) Malak, Piotr; Letowska, Agnieszka; Wodzinski, Jan; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
We present a multilayered methodology for processing digitized historical texts, enabling cross-relational analysis across time periods, languages, and subject domains. Drawing from multiple DH platforms (Tsadikim, Two Enlightenments, Corporeality), we demonstrate an integrated pipeline combining adaptive OCR, noise-tolerant keyword extraction, and NER. Custom preprocessing and fuzzy matching techniques allow for meaningful text recovery from degraded scans in Polish, German, and Yiddish. Data are enriched with spatial and temporal metadata, indexed by topic and linked across projects. The resulting datasets support trend analysis, social network modeling, and discourse mapping. Our approach enables researchers to trace linguistic shifts and intellectual networks over centuries without manual review of source pages. This workflow facilitates interoperable exploration of cultural data and demonstrates how machine learning can assist in recovering semantic relationships from fragmented historical records. The methodology was tested on Enlightenment-era and early 20th-century journals, revealing both technical challenges and insights into evolving ideological, medical, and theological vocabularies.
HBIM Modelling Techniques Applied to Gothic Architecture: Insights from the Founder's Chapel at the Monastery of Batalha
(The Eurographics Association, 2025) Sugiyama, Gabriel; Rodrigues, Hugo; Rodrigues, Fernanda; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Heritage Building Information Modelling (HBIM) emerged as a pivotal tool for documenting and preserving built heritage, yet practitioners face significant challenges in selecting optimal modelling approaches for complex historic structures. This study presents a comprehensive comparison of HBIM modelling techniques applied to the Founder's Chapel of the Monastery of Batalha (Monastery of Santa Maria da Vitória), a masterpiece of Portuguese Late Gothic architecture. Through a systematic analysis of three distinct modelling techniques - parametric modelling, NURBS modelling, and mesh-based reconstruction - this work evaluates their effectiveness in capturing the chapel's intricate architectural elements, focussing on its vaults. The research employed point cloud data obtained using terrestrial laser scanning as the basis for modelling. The comparative assessment focused on three key parameters: geometric accuracy, time efficiency, and model flexibility. The results indicate that parametric modelling offers the possibility to establish relations to the surrounding architectural elements and a high degree of adaptability, NURBS modelling provides geometrically accurate surfaces through mathematically defined curves and control points, while mesh representation provides exceptional fidelity in documentation. This study demonstrates that the most effective strategy for comprehensive documentation incorporates parametric modelling as the foundation within HBIM frameworks, complemented by the remaining techniques according to the model's purpose. This integrated approach harnesses the distinctive strengths of each method while counterbalancing their respective limitations, resulting in a more complete digital representation of the built heritage. The results suggest that the choice of modelling approach should be driven by project-specific requirements rather than technical preferences, with particular consideration given to the intended use of the model. The results provide valuable information for heritage professionals in selecting appropriate HBIM modelling strategies, while also highlighting the need for improved interoperability between complementary approaches.
High-Resolution LiDAR for Archaeological Prospection in Mediterranean Forested Landscapes: Insights from Two Case Studies in Italy
(The Eurographics Association, 2025) Cirigliano, Giuseppe Prospero; Mazzacca, Gabriele; Remondino, Fabio; Liverani, Paolo; Cantoro, Gianluca; Pocobelli, Giorgio; Maschner, Herbert; Campana, Stefano; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
This paper presents the results of two high-resolution airborne LiDAR surveys carried out in Mediterranean forested environments with rich archaeological potential. These case studies, located in southern Tuscany and within the presidential estate of Castel Porziano near Rome, illustrate the value of LiDAR-based approaches for identifying and interpreting cultural landscapes that are otherwise obscured by dense vegetation. In the Tuscan case study, which includes the ancient settlement of Roselle and the nearby hill of Moscona, UAV-mounted LiDAR sensors were employed to acquire data over an area of approximately 550 hectares. The resulting point clouds, with an average density of 750 points per square meter, allowed for the detection of subtle topographic features and archaeological structures, including buried walls, road systems, and necropolises. The complexity of the dataset required the development of a multi-stage processing pipeline, combining deep learning techniques and semantic segmentation to differentiate ground surfaces, vegetation, and structural elements, ultimately leading to the creation of detailed Digital Terrain and Feature Models (DTMs and DFMs). Conversely, the Castel Porziano survey covered a large protected area with limited modern disturbance and dense coastal vegetation. While the LiDAR dataset was acquired via manned airborne platforms due to legal and logistical restrictions on drone flights, the results proved equally rich in archaeological information. The high-resolution data enabled a diachronic interpretation of the landscape and revealed patterns of land use, infrastructural networks, and traces of earlier human occupation previously undocumented due to the site's inaccessibility and forest coverage. While the technological setup differed between the two contexts, particularly with regard to drone deployment, the central role of high-resolution LiDAR remains consistent. The comparison between these case studies highlights how adaptable and powerful LiDAR technology can be in supporting archaeological research in forested Mediterranean environments. Moreover, the integration of computational techniques such as AI-driven classification and multi-resolution analysis provides scalable solutions for managing large datasets and improving archaeological feature extraction. This contribution emphasizes not only the methodological advancements enabled by LiDAR and AI integration but also the importance of interdisciplinary collaboration between archaeologists, remote sensing specialists, and data scientists. It offers a flexible framework applicable to other Mediterranean contexts where environmental constraints, dense vegetation, and heritage protection pose challenges to traditional archaeological methods.
IBE meets AIR: a framework for structured archaeological reasoning and digital reconstruction
(The Eurographics Association, 2025) Campanaro, Danilo Marco; Derudas, Paola; Thomsen, Mikkel H.; Foley, Brendan; Nurra, Federico; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
The increasing use of digital tools in archaeology has vastly expanded our capacity to document and visualise the past, yet the reasoning that connects evidence to interpretation often remains implicit or undocumented. This paper addresses that gap by integrating Inference to the Best Explanation (IBE)-a philosophical model of hypothesis evaluation-into the Archaeological Interactive Report (AIR), a semantic platform for managing and visualising archaeological data. We demonstrate how this integration enables transparent, iterative, and reproducible archaeological interpretation by structuring hypotheses, linking them to evidence, and assessing them against explanatory virtues. Two case studies illustrate the potential of this framework: the systematic reconstruction of the House of the Greek Epigrams in Pompeii, and an experimental application to the Gribshunden shipwreck, where reasoning evolves alongside data collection. The result is a replicable method that formalises archaeological argumentation and embeds it directly within digital infrastructure, making interpretation not only visible, but critically assessable and reusable.
Identification of Violin Reduction via Contour Lines Classification
(The Eurographics Association, 2025) Beghin, Philémon; Ceulemans, Anne-Emmanuelle; Glineur, François; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
The first violins date back to the end of the 16th century in Italy. For around 200 years, these instruments have spread throughout Europe and luthiers of various royal courts, eager to experiment with new techniques, created a highly diverse family of instruments. In an attempt to normalise violins for European orchestras and conservatories, size standards were imposed around 1750. Instruments that fell between two standards were then reduced to a smaller size by luthiers. These reductions have an impact on several characteristics of violins, in particular on the contour lines, i.e. lines of constant altitude as measured from a reference plane between the violin plates, which look more like a 'U' for non reduced instruments and a 'V' for reduced ones. Those differences between (un)reduced violins have been observed empirically but to our knowledge no quantitative study has been carried out on the subject. In this paper, we aim at developing a tool for classifying violin contour lines in order to distinguish reduced instruments from non reduced instruments. We study a corpus of 25 instruments whose 3D geometric meshes have been acquired via photogrammetry. For each instrument, we sample contour lines at 10-20 levels, regularly spaced every millimetre. Each contour line is fitted with a parabola-like curve (with an equation of the type $y = \alpha |x|^\beta$) depending on two parameters, describing how open ($\beta$) and how vertically stretched ($\alpha$) the curve is. We compute additional features from those parameters, using regressions and counting how many values fall under some threshold. We also deal with outliers and non equal numbers of levels, and eventually obtain a numerical profile for each instrument. We then applied different learning techniques on those profiles to determine whether instruments can be classified solely according to their geometry. We find that distinguishing between reduced and non reduced instruments is feasible to some degree, taking into account that a whole spectrum of more or less transformed violins exists, for which it is more difficult to quantify the reduction. We also find the opening parameter $\beta$ to be the most predictive.
The IlluminAI project: a deep neural network and immersive visualization system to enhance illuminated manuscripts
(The Eurographics Association, 2025) Minisini, Valeria; Gosti, Giorgio; Fanini, Bruno; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
In museum and archive digital catalogues, illuminated manuscript pages can often be found within heterogeneous groups of reproductions, coexisting with other types of artworks and objects. With them, figurative miniatures share the depicted subjects that are recognizable, regardless of the medium used, for their specific iconography. Thanks to the use of a visual vocabulary still common today, illuminations are also the element that mostly attracts the non-academic public, making the often-incomprehensible content partly accessible despite the language. The paper will present IlluminAI, a project still in progress, which aims at the enhancement of late medieval and Renaissance illuminated codices using artificial intelligence through an immersive visualization system capable of automatically recognizing manuscript sheets, analyzing their content, and relating specimens with similar illustrations or artworks from the same theme. After some brief references to contextualize the work, we will expose the first completed phase of the research focusing on the original dataset composition before outlining the chosen semi-automatic labeling strategy and the interactive machine learning approach. This was used to create with transfer learning a model able to recognize manuscript pages and identify inside of them five characteristic layout elements. We will then switch to the second ongoing part of the project with the design of the immersive Web3D system, based on the open-source ATON framework, that will give users the possibility to explore, inspect, compare and query large amounts of images in a three-dimensional space. The data aggregation criteria and the presentation modes will be described with particular attention to the spatial organization and novel 3D interfaces.
Innovative Approaches through 3D Survey and Virtual Technologies for the Geometric and Semantic Fruition of Built Heritage Sites on the Web
(The Eurographics Association, 2025) Aricò, Manuela; Cherif, Souhir; Guardia, Marcello La; Brutto, Mauro Lo; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Nowadays recent advances in Geomatics and Computer Science led specialists to explore new methodologies for the preservation and valorization of Built Heritage (BH). In fact, if on one hand the preservation of monumental complexes needs to remotely manage virtual representations of the real environments to be preserved, on the other hand the valorization allows visitors to virtually explore BH sites in remote, thanks to the spread of web technologies. The main challenges about the virtual fruition of BH sites are related to the management of 3D big data digitized geometries and the requirement for property software-based solutions. This work explores a possible strategy, based on open-source technologies for the web fruition of 3D geometric and semantic information of BH sites from 3D digitization. The first results of this research are related to the cloister of the Cathedral of Cefalù (Italy), which represents a classic example of a BH site that, for its extraordinary importance and its state of preservation, could benefit from the application of virtual technologies for conservation and fruition purposes. The work describes the acquisition of the 3D geometric dataset through laser scanner and photogrammetric surveys, its optimisation, and the design of a web-based platform for the fruition online of 3D geometric and semantic information. The web navigation system was developed through Three.js JavaScript WebGL libraries, inside a HTML5 compliant environment, connected in real-time to Postgres Relational Database Management System through the activation of a Python module in an Anaconda platform. In this way, the geometric information, hosted by the WebGL environment, was connected in real-time to the semantic information stored in the database. This system represents a prototypical structure for the future development of a full platform for the web exploration and management of BH sites developed with low-cost technologies and useful for a large variety of stakeholders (from municipalities to private companies) who manage BH sites.
Intra-site Spatial Analysis at Sambuco Cave: Testing Digital 3D Approach for the Interpretation of Upper Palaeolithic Behavioural Strategies
(The Eurographics Association, 2025) Pizziolo, Giovanna; Tessaro, Carlo; Faraoni, Matteo; Mustone, Gaia; Galiberti, Attilio; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Sambuco Cave, located in central Italy, preserves a stratified sequence from the Upper Palaeolithic to the Neolithic, making it an important archaeological site. This research combines traditional excavation data with Digital Heritage methodologies to enhance the understanding of site formation and spatial organization within the cave. A 3D GIS-based workflow integrates photogrammetric documentation, lithic analysis, and spatial modelling to reconstruct prehistoric behaviours and identify activity zones. The study highlights the importance of virtual reconstructions in clarifying stratigraphic relationships and interpreting the cave's usage. Results suggest a focused, task-specific occupation pattern, emphasizing short-term use, possibly related to hunting and toolmaking. This innovative approach provides valuable insights into Upper Palaeolithic settlement strategies and offers a new perspective on the spatial organization of prehistoric sites. At present, this paper represents an experimental 3d analytical approach presented here as a methodological test.
Mapping Pausania: A GIS-Based Reconstruction of the Laconian Landscape
(The Eurographics Association, 2025) Cornaglia, Marco; Barzaghi, Sebastian; Iannucci, Alessandro; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
The archaeological landscape of ancient Greece is a paradigmatic case study for cultural heritage research, not only because of the sheer amount of identified remains, but also because of the many ancient texts referring to such elements. In this regard, among the surviving literary works from antiquity, the Periegesis of Pausanias represents a valuable asset, whose exhaustiveness in firsthand descriptions has exerted a strong influence on modern research. The narrative of the text, structured as a series of itineraries, is particularly suitable for the creation of digital maps which may recreate ancient landscapes and compare them with the current state of research. In particular, the region of Laconia has proven to be promising in light of the state of partial decay already observed in Roman times, by the time of the author's analysis. Therefore, the area has been isolated as a case study and recreated in the form of three GIS maps by using the ArcGIS software, focusing respectively on Laconia in the classical age, in the Roman age, and in the current state. As such, the three maps may be used simultaneously for synchronic and diachronic investigations of the region, thereby enabling the evaluation of the peculiarities of the studied landscape and heritage. The data visualized in the digital maps is derived from a critical analysis of the text and associated with comments based on the state of the art, which not only enhance the study of the mapped remains but also allow for the assessment of the state of identification of the landscape treated by Pausanias. The georeferenced database, built to support the spatial analysis and the data visualization, aims to overcome the limitations generally inherent to other thesauri and gazetteers of the classical world, thanks to a taxonomy that allows for the rapid isolation of salient features of the mapped data. Data such as the time period, the actual state of identification, modern toponymy, and the typology of the remains can be quickly researched, thus enabling several kinds of queries. All the produced cartography is also intended to be uploaded online by using the ArcGIS Online cloud platform, with the aim to create a web application that ensures maximum visibility and easy access to the mapped material.
NL-2-SPARQL: Ontology-Based Natural Language Querying over 3D Point Cloud Knowledge Graphs
(The Eurographics Association, 2025) Codiglione, Matteo; Remondino, Fabio; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Point clouds are an asset in a wide range of applications, including heritage monitoring and conservation. However, querying capabilities over such 3D datasets, a fundamental task for their practical usability, is often highly challenging. In particular, difficulties arise when it comes to natural language querying, which can be in turn highly useful in lowering the technical barrier in inspecting 3D point clouds. The present paper explores various approaches for natural language querying over point clouds, leaning for the SPARQL-based query system allowed by the 3DOnt framework for point clouds management, recasting the problem as a natural language to SPARQL translation. After reviewing existing methodologies, we propose NL-2- SPARQL, a novel and flexible neuro-symbolic approach that integrates a Large Language Model (LLM) with a Graph Exploration and Query Building tool (GEQB). We then evaluate this method and demonstrate its application within the 3DOnt framework, highlighting its broader applicability to knowledge graphs in general, beyond this specific 3D-oriented context. A video presentation of the 3DOnt framework is available at https://3dom.fbk.eu/projects/3DOnt.
An Open-Source Workflow for Handwritten Character Recognition
(The Eurographics Association, 2025) Imboden, Silvano; Guidazzoli, Antonella; Cardano, Giorgia; Mattei, Luca; Andrucci, Federico; Shemek, Deanna; Pansini, Rossella; Albertin, Fauzia; Liguori, Maria Chiara; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
The rich manuscript heritage of Italy, preserved in archives and libraries, is becoming increasingly accessible to a wider audience through dedicated digitization initiatives. However, the interpretation of these manuscripts often proves challenging due to several factors: the linguistic complexity of medieval Latin, the early development of vernacular languages, the continuous evolution of handwriting styles, and the extensive use of abbreviation systems devised to conserve space on costly materials such as parchment and paper. The Artificial Intelligence (AI) tools can significantly boost the last step of the digitization process: the transcription. In particular, the advent of the Handwritten Character Recognition (HCR) technology enables recognition and processing of handwritten text. However, as with all AI tools - especially in the domain of handwritten texts and, more broadly, in the Humanities, training and fine-tuning is required. To support Digital Humanists in tailoring these powerful tools to specific needs - i.e. transcribing different handwriting styles - a Human-AI collaboration approach has been adopted to develop a collaborative web application, named HCR WORKFLOW, designed for the creation of ground-truth data for AI-based manuscript transcription. The platform is composed by a toolkit for document layout analysis based on Neural Networks for text line recognition (P2PaLA), an image Transformer encoder and an autoregressive text Transformer decoder for single-line transcription (TrOCR). This integrated system guides and assists Digital Humanists throughout the entire process - from digitization to transcription supervision. For this study, the platform was used to fine-tune TrOCR on the humanistic script, and in particular to create the ground truth basing on the Copialettere (Letterbooks) of Isabella d'Este and the letters of Lucrezia Borgia. This research paper will discuss in detail the HCR WORKFLOW platform,the dataset used, the approach to create a AI-oriented transcription, and the results of the fine-tuning of the AI tool for manuscript transcription.
Outside the Wall: Some Applications of TagLab for Semantic Segmentation in Archaeological Practice
(The Eurographics Association, 2025) Ronchi, Diego; Virgilio, Elisabetta Di; Mele, Samira; Lombardi, Matteo; Ferdani, Daniele; Dininno, Domenica; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
Imaging techniques have a long history in archeology, from the ruins depicted during the Grand Tour to today's large-scale photogrammetric surveys. Orthophotos generated with photogrammetry are currently extensively used in archeology: a key challenge in this new documentation paradigm lies in the semantic segmentation of such pixel matrices, a process increasingly aided by Machine Learning. This paper focuses on TagLab, an open-source tool originally developed for marine biology that has proven to be extremely versatile in archeological practice. More specifically, this paper aims to expand the use of the software in the Cultural Heritage field and explore its applicability for cost estimation on ancient construction sites, archeological excavations, ceramic thin sections and fragmentary painting documentation.
Palazzo della Loggia According to Luigi Vanvitelli: a Digital Reconstruction
(The Eurographics Association, 2025) Matteis, Silvia De; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
This paper aims to describe the process of 3D Reconstruction of Luigi Vanvitelli's (Naples, 1700 - Caserta, 1773) second design for the Great Hall of the Palazzo della Loggia in Brescia, and the drawing analysis that it entailed. In 1575, the 16th-century Loggia was consumed by a fire that devastated first floor interior and roof, but left the lower floor and the exterior largely unscathed. The roof was hastily repaired, the still-serviceable areas sectioned off, and the building languished in this precarious state for nearly two centuries. Eventually, local authorities commissioned its restoration (1764). Due to the monument's significance, Vanvitelli needed to utilize the pre-existing structure, damaged though it may be. These constraints resulted in two designs, drafted between 1769 and 1771, which displayed the same radial distribution but differed in the shape of the plan (circular and octagonal, respectively). Construction of the 1771 design began after Vanvitelli's death, and only reached the entablature before halting indefinitely. This paper aims to describe the challenges and questions posed by the process of 3D reconstruction of Luigi Vanvitelli's second design for the Great Hall (Salone) of the Palazzo della Loggia in Brescia, particularly with regards to the articulation of the vault. The reconstructions are based on two series of drawings in the hand of Vanvitelli and Piermarini, presently hosted at the Archivio di Stato di Brescia, occasionally interpolated with the information that can be gleaned from Baldassarre Zambone's engravings (1778). Three potential geometric interpretations, which the present paper seeks to explore, were identified by analyzing the area of the vault, first through the lens of ''necessary'' (brought about by the transition from circle to octagon) versus unforced changes, and then in light of the discrepancies found both within and among the drawings.

Browse

Browsing Track 05 – Analysis and Interpretation by Title

Results Per Page

Sort Options