SUN’IY INTELLEKT YORDAMIDA TASVIRIY SAN’AT ASARLARINI REKONSTRUKSIYA QILISH VA RESTAVRATSIYA QILISH USULLARI: NAZARIY ASOSLAR VA AMALIY YONDASHUVLAR

Abdullayev O‘ktamjon Ergashevich; Matkarimov Abduraxim Muxammadjonovich

doi:10.5281/zenodo.19829075

25.04.2026

Oʻzbekcha

SUN’IY INTELLEKT YORDAMIDA TASVIRIY SAN’AT ASARLARINI REKONSTRUKSIYA QILISH VA RESTAVRATSIYA QILISH USULLARI: NAZARIY ASOSLAR VA AMALIY YONDASHUVLAR

Published

25.04.2026

Journal

Priority areas for applying artificial intelligence to pedagogical education

Issue

Priority areas for applying artificial intelligence to pedagogical education

Pages

327-331

DOI

10.5281/zenodo.19829075

Authors

Abdullayev O‘ktamjon Ergashevich , Matkarimov Abduraxim Muxammadjonovich

Abstract

Mazkur maqolada sun’iy intellekt texnologiyalarining tasviriy san’at asarlarini rekonstruksiya qilish va restavratsiya qilish jarayonidagi o‘rni chuqur ilmiy yondashuv asosida tahlil qilinadi. Tadqiqotda zamonaviy algoritmlar, xususan, chuqur o‘rganish (deep learning), generativ modellar, konvolyutsion neyron tarmoqlar (CNN), va diffuzion modellar asosida tasvirlarni tiklash usullari keng ko‘rib chiqiladi. Shuningdek, tarixiy san’at asarlarining degradatsiyasi, ularni raqamli tiklash muammolari, shovqinlarni kamaytirish, ranglarni tiklash va yo‘qolgan fragmentlarni qayta yaratish kabi masalalar muhandislik nuqtai nazaridan yoritiladi. Maqolada sun’iy intellektning san’atni saqlash va tiklashdagi innovatsion imkoniyatlari bilan birga uning cheklovlari va etik jihatlari ham muhokama qilinadi.

Keywords

neyron tarmoqlar sun’iy intellekt tasviriy san’at rekonstruksiya restavratsiya deep learning generativ modellar image inpainting super-resolution kompyuter ko‘rish

Other language versions

Русский

sun’iy intellekt, tasviriy san’at, rekonstruksiya, restavratsiya, neyron tarmoqlar, deep learning, generativ modellar, image inpainting, super-resolution, kompyuter ko‘rish

глубокое обучение искусственный интеллект компьютерное зрение нейронные сети изобразительное искусство реконструкция реставрация генеративные модели восстановление изображений сверхвысокое разрешение

English

This article analyzes the role of artificial intelligence technologies in the reconstruction and restoration of works of fine art based on a deep scientific approach. The study extensively examines methods for restoring images based on modern algorithms, in particular, deep learning, generative models, convolutional neural networks (CNN), and diffusion models. It also covers issues such as the degradation of historical works of art, the problems of their digital restoration, noise reduction, color restoration, and the reconstruction of lost fragments from an engineering perspective. The article discusses the innovative potential of artificial intelligence in the preservation and restoration of art, as well as its limitations and ethical aspects.

artificial intelligence computer vision deep learning neural networks fine art reconstruction restoration generative models image inpainting super-resolution

References

1. Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. Cambridge: MIT Press, 2016.

2. Richard Szeliski. Computer Vision: Algorithms and Applications. London: Springer, 2010.

3. Alexey Dosovitskiy va boshqalar. “Image Generation with Deep Learning: A Survey.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.

4. Jonathan Ho, Ajay Jain, Pieter Abbeel. “Denoising Diffusion Probabilistic Models.” Advances in Neural Information Processing Systems (NeurIPS), 2020.

5. Raymond H. Chan, Jacky K. H. Ng. “Image Restoration: Fundamentals and Advances.” SIAM Review, 2011.

6. Gustavo Carneiro, Jaco van de Weijer. “Deep Learning for Image Restoration and Reconstruction: A Survey.” IEEE Access, 2020.

View PDF