Deep Learning Techniques for Archaeological Image Restoration

Ajinkya Kulkarni, Prajwal Naduvinamath, Ganesh Naik, Sneha Totad, Uday Kulkarni, Shashank Hegde

2025

Abstract

Archaeological sites, rich in historical and cultural significance, face deterioration from invasive, environmental, biological and natural factors, necessitating innovative restoration methods. The proposed paper introduces a U-Net-based Generative Adversarial Network (GAN) framework to reconstruct damaged temple images, ensuring the preservation of intricate architectural details. A custom dataset of masked images was created, and the model was trained to reconstruct missing sections while balancing adversarial and reconstruction losses for realistic outputs. The proposed approach addresses challenges in traditional techniques by restoring complex textures, enhancing fine details and producing visually coherent results, achieving a Structural Similarity Index Measure (SSIM) of 0.7128. Furthermore, the framework demonstrates robustness in handling various levels of damage and noise, paving the way for scalable applications in heritage conservation. The proposed work contributes significantly to cultural heritage preservation by combining advanced deep learning methodologies with precise evaluation metrics to achieve impactful results.

Paper Citation

in Harvard Style

Kulkarni A., Naduvinamath P., Naik G., Totad S., Kulkarni U. and Hegde S. (2025). Deep Learning Techniques for Archaeological Image Restoration. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 26-32. DOI: 10.5220/0013608100004664

in Bibtex Style

@conference{incoft25,
author={Ajinkya Kulkarni and Prajwal Naduvinamath and Ganesh Naik and Sneha Totad and Uday Kulkarni and Shashank Hegde},
title={Deep Learning Techniques for Archaeological Image Restoration},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT},
year={2025},
pages={26-32},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013608100004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT
TI - Deep Learning Techniques for Archaeological Image Restoration
SN - 978-989-758-763-4
AU - Kulkarni A.
AU - Naduvinamath P.
AU - Naik G.
AU - Totad S.
AU - Kulkarni U.
AU - Hegde S.
PY - 2025
SP - 26
EP - 32
DO - 10.5220/0013608100004664
PB - SciTePress