Enhancing Cultural Heritage with Generative AI: A Comparative Framework for the Evaluation of 3D Model Accuracy and Visual Fidelity

Simple item page
dc.contributor.authorBalloni, Emanueleen_US
dc.contributor.authorPaolanti, Marinaen_US
dc.contributor.authorUggeri, Jacopoen_US
dc.contributor.authorZingaretti, Primoen_US
dc.contributor.authorPierdicca, Robertoen_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.accessioned2025-09-05T20:25:51Z
dc.date.available2025-09-05T20:25:51Z
dc.date.issued2025
dc.description.abstractThe 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.en_US
dc.description.sectionheadersAnalysing and Documenting Digitized Assets
dc.description.seriesinformationDigital Heritage
dc.identifier.doi10.2312/dh.20253146
dc.identifier.isbn978-3-03868-277-6
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/dh.20253146
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/dh20253146
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Artificial intelligence; 3D imaging; Computer graphics; Image-based rendering; Information systems → Multimedia content creation
dc.subjectComputing methodologies → Artificial intelligence
dc.subject3D imaging
dc.subjectComputer graphics
dc.subjectImage
dc.subjectbased rendering
dc.subjectInformation systems → Multimedia content creation
dc.titleEnhancing Cultural Heritage with Generative AI: A Comparative Framework for the Evaluation of 3D Model Accuracy and Visual Fidelityen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dh20253146.pdf
Size:
13.03 MB
Format:
Adobe Portable Document Format
Download
Collections
Track 05 – Analysis and Interpretation