Digital Inpainting of Damaged Frescoes Using a Fine-Tuned Diffusion Model

Simple item page
dc.contributor.authorSmolka, Milenaen_US
dc.contributor.authorSmolka, Bogdanen_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.accessioned2025-09-05T19:05:45Z
dc.date.available2025-09-05T19:05:45Z
dc.date.issued2025
dc.description.abstractFrescoes are a vital part of cultural heritage, but they are increasingly deteriorating due to environmental and human factors. Traditional restoration methods are costly, labor-intensive, and may risk compromising the original artwork-particularly when the damaged content is uncertain. These challenges highlight the need for innovative approaches that can complement conventional techniques. This paper explores the application of a deep learning-based method for the virtual restoration of frescoes. The focus is on image inpainting, a process that fills in missing fragments by leveraging information from the undamaged parts of the image, while preserving consistency in texture, color, and artistic style. When enhanced by deep learning models, this approach enables the generation of realistic reconstructions, even for areas where the original appearance is unknown. The study evaluates the effectiveness of fine-tuned models in restoring both minor and major damage, such as small cracks and missing sections, using different sets of hyperparameters. Model performance was assessed using a combination of objective quality metrics and subjective evaluations. Additionally, an intuitive web-based tool was developed to make the restoration process more accessible and user-friendly.en_US
dc.description.sectionheadersInstrumental and Computational Approaches for CH Conservation and Restauration
dc.description.seriesinformationDigital Heritage
dc.identifier.doi10.2312/dh.20253072
dc.identifier.isbn978-3-03868-277-6
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/dh.20253072
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/dh20253072
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; Computer vision; Reconstruction
dc.subjectComputing methodologies → Artificial intelligence
dc.subjectComputer vision
dc.subjectReconstruction
dc.titleDigital Inpainting of Damaged Frescoes Using a Fine-Tuned Diffusion Modelen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dh20253072.pdf
Size:
10.66 MB
Format:
Adobe Portable Document Format
Download
Collections
Track 01 – Documentation, Preservation, Monitoring and Restoration