Photorealistic Texture Contextual Fill-In

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F25%3A00381960" target="_blank" >RIV/68407700:21240/25:00381960 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.3390/heritage8010009" target="_blank" >https://doi.org/10.3390/heritage8010009</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/heritage8010009" target="_blank" >10.3390/heritage8010009</a>

Result language

angličtina

Original language name

Photorealistic Texture Contextual Fill-In

Original language description

This paper presents a comprehensive study of the application of AI-driven in painting techniques to the restoration of historical photographs of the Czech city Most, with a focus on restoration and reconstructing the lost architectural heritage. The project combines state-of-the-art methods, including generative adversarial networks (GANs), patch-based inpainting, and manual retouching, to restore and enhance severely degraded images. The reconstructed/restored photographs of the city Most offer an invaluable visual representation of a city that was largely destroyed for industrial purposes in the 20th century. Through a series of blind and informed user tests, we assess the subjective quality of the restored images and examine how knowledge of edited areas influences user perception. Additionally, this study addresses the technical challenges of inpainting, including computational demands, interpretability, and bias in AI models. Ethical considerations, particularly regarding historical authenticity and speculative reconstruction, are also discussed. The findings demonstrate that AI techniques can significantly contribute to the preservation of cultural heritage, but must be applied with careful oversight to maintain transparency and cultural integrity. Future work will focus on improving the interpretability and efficiency of these methods, while ensuring that reconstructions remain historically and culturally sensitive.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/DH23P03OVV048" target="_blank" >DH23P03OVV048: Most – a city that did not disappear</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Heritage

ISSN

2571-9408

e-ISSN

2571-9408

Volume of the periodical

8

Issue of the periodical within the volume

1

Country of publishing house

CH - SWITZERLAND

Number of pages

21

Pages from-to

—

UT code for WoS article

001403854900001

EID of the result in the Scopus database

2-s2.0-85215824041