magistrsko delo
Gal Menaše (Author), Franc Solina (Mentor), Borut Batagelj (Co-mentor)

Abstract

Magistrsko delo obravnava uporabo globokega učenja za rekonstrukcijo manjkajočih delov arheoloških artefaktov, s poudarkom na 2D slikah fresk in mozaikov. Tradicionalne restavratorske metode so dolgotrajne, drage in pogosto nereverzibilne, zato smo raziskali avtomatizirane pristope z uporabo umetne inteligence, natančneje modela Stable Diffusion XL (SDXL). Z uporabo tehnike LoRA smo model prilagodili specifičnemu slogu avtorja ali podobnih del in ga uporabili za rekonstrukcijo fresk iz cerkve Device Marije v Polju, Vile misterij v Pompejih, Frančiškanske cerkve v Ljubljani ter mozaika iz Mošenj. Učinkovitost rekonstrukcij smo ovrednotili s kvantitativnima metrikama SSIM in LPIPS ter kvalitativnimi ocenami strokovnjakov. Rezultati kažejo, da so rekonstrukcije vizualno prepričljive, vendar zahtevajo poglobljeno razumevanje ikonografije in konteksta za zagotavljanje zgodovinske natančnosti. Predlagani pristop predstavlja hitrejšo in cenovno ugodnejšo alternativo tradicionalnim metodam, a za etično in natančno restavriranje zahteva nadaljnje izboljšave, zlasti pri vključevanju ikonografskih referenc.

Keywords

računalniški vid;globoko učenje;varstvo kulturne dediščine;rekonstrukcija artefaktov;manjkajoči deli;3D modeliranje;umetna inteligenca;računalništvo;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [G. Menaše]
UDC: 004.93:7.025.4(043.2)
COBISS: 247600131 Link will open in a new window
Views: 52
Downloads: 9
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Reconstruction of missing parts of artifacts
Secondary abstract: This master's thesis explores the use of deep learning for the reconstruction of missing parts of archaeological artifacts, focusing on 2D images of frescoes and mosaics. Traditional restoration methods are time-consuming, costly, and often irreversible, prompting an investigation into automated approaches using artificial intelligence, specifically the Stable Diffusion XL (SDXL) model. The base model was fine-tuned using the LoRA technique to capture the style of the same artist or similar works and applied to case studies involving frescoes from the Church of the Virgin Mary in Polje, the Villa of the Mysteries in Pompeii, the Franciscan Church in Ljubljana, and a mosaic from Mošnje. The reconstructions were evaluated using quantitative metrics SSIM and LPIPS, as well as qualitative assessments by an expert. The results demonstrate that the reconstructions are visually compelling but require additional understanding of iconography and context to ensure historical accuracy. The proposed approach offers a faster and more cost-effective alternative to traditional methods, though it necessitates further improvements in incorporating iconographic references for ethical and precise restoration.
Secondary keywords: computer vision;deep learning;cultural heritage protection;artifact reconstruction;missing parts;3D modeling;artificial intelligence;computer science;master's degree;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 1 spletni vir (1 datoteka PDF (59 str.))
ID: 27231987