A multimodal approach to 3D modelling of Spanish cultural heritage buildings for visualization and management based on generative AI and geospatial data

Simple item page
dc.contributor.authorBarbero-Álvarez, Miguel Antonioen_US
dc.contributor.authorPeña, Javier Rodríguezen_US
dc.contributor.authorFerrero, Cristian Olmedoen_US
dc.contributor.authorAlonso, Marina A. Álvarezen_US
dc.contributor.editorCampana, Stefanoen_US
dc.contributor.editorFerdani, Danieleen_US
dc.contributor.editorGraf, Holgeren_US
dc.contributor.editorGuidi, Gabrieleen_US
dc.contributor.editorHegarty, Zackaryen_US
dc.contributor.editorPescarin, Sofiaen_US
dc.contributor.editorRemondino, Fabioen_US
dc.date.accessioned2025-09-05T20:34:25Z
dc.date.available2025-09-05T20:34:25Z
dc.date.issued2025
dc.description.abstractThis work presents a study on blending the latest artificial intelligence technologies with geospatial data for managing and visualizing Spain's cultural heritage. The goal is to achieve a new stable simulation using multimodal data that serves as a foundation for future advancements in AI-driven cultural heritage 3D modeling technology. Fundamentally, the work here exposed is a proof of concept to assess whether the exploration and visualization of the geospatial information related to Spain's cultural heritage can rely on AI concepts to improve its processing and understanding. This will lay ground for enhancing the visitor experience at heritage sites within their contextual environment. The application of the proposed methodology to a real-world case, such as the Monastery of El Escorial, has demonstrated the potential of generative AI in the management and dissemination of cultural heritage resources. This method is innovative because it proposes a new approach in which the combination of different AI-generated results serves as the starting point for creating 3D models of buildings, which can be manually refined aftwerwards, instead of the more costly manual acquisition and modelling from scratch. The approach integrates multimodal sources of graphical information, including videos, photographs, and text, to be blended with geospatial data. It is concluded that design methods integrating AI techniques and geospatial data add quality to working models, given that buildings are inherently tied to their spatial context. The addition of these properties allows for a more precise and detailed digital representation. Furthermore, these models can be visualized in web applications, thus shedding light on AI as a valuable tool to be added to the already existing modelling solutions in digital cultural heritage.en_US
dc.description.sectionheadersAI and Generative Techniques for Heritage Reconstruction
dc.description.seriesinformationDigital Heritage
dc.identifier.doi10.2312/dh.20253085
dc.identifier.isbn978-3-03868-277-6
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/dh.20253085
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/dh20253085
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleA multimodal approach to 3D modelling of Spanish cultural heritage buildings for visualization and management based on generative AI and geospatial dataen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dh20253085.pdf
Size:
11.79 MB
Format:
Adobe Portable Document Format
Download
Collections
Track 06 – Visualization and Interaction