Automated Image Inpainting for Historical Artifact Restoration Using Deep Generative Models
Keywords:
Image Inpainting, Historical Artifact Restoration, Generative Adversarial Networks (GANs), Deep Generative Models, Cultural Heritage PreservationAbstract
Historical artifacts often suffer degradation due to aging, environmental exposure, and mishandling, leading to partial loss of visual content. Manual restoration is time-consuming, expertise-driven, and prone to subjectivity. Automated image inpainting techniques using deep generative models provide a scalable solution for artifact preservation by reconstructing missing regions with semantically consistent content. In this paper, we propose a generative adversarial network (GAN)-based approach for historical artifact restoration, capable of capturing both global structures and fine textures. The model integrates perceptual loss, adversarial loss, and structural similarity constraints to ensure high-fidelity reconstructions. Experimental results on benchmark datasets demonstrate superior performance compared to conventional inpainting methods, with improvements in Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Fréchet Inception Distance (FID). Furthermore, we provide a case study on digitized cultural heritage artifacts, showcasing the potential of our approach in museum preservation and archival digitization.
Downloads
References
M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” Proc. ACM SIGGRAPH, pp. 417–424, 2000.
A. Criminisi, P. Pérez, and K. Toyama, “Region filling and object removal by exemplar-based inpainting,” IEEE Trans. Image Process., vol. 13, no. 9, pp. 1200–1212, 2004.
J. Mairal, M. Elad, and G. Sapiro, “Sparse representation for color image restoration,” IEEE Trans. Image Process., vol. 17, no. 1, pp. 53–69, 2008.
D. Pathak, P. Krahenbuhl, J. Donahue, T. Darrell, and A. Efros, “Context encoders: Feature learning by inpainting,” Proc. CVPR, pp. 2536–2544, 2016.
GS Naveen Kumar, VSK Reddy , “A Scheme for Shot Detection and Video Retrieval using Spatio Temporal Features”, International Journal of Recent Technology and Engineering (IJRTE), ISSN: 2277-3878, Volume-8 Issue-2S10, September 2019.
J. Johnson, A. Alahi, and L. Fei-Fei, “Perceptual losses for real-time style transfer and super-resolution,” Proc. ECCV, pp. 694–711, 2016.
J. Yu, Z. Lin, J. Yang, X. Shen, X. Lu, and T. Huang, “Generative image inpainting with contextual attention,” Proc. CVPR, pp. 5505–5514, 2018.
K. Nazeri, E. Ng, T. Joseph, F. Qureshi, and M. Ebrahimi, “EdgeConnect: Structure guided image inpainting using edge prediction,” Proc. ICCV Workshops, pp. 3265–3274, 2019.
J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” Adv. Neural Inf. Process. Syst., pp. 6840–6851, 2020.
Naveen Kumar, G.S., Venkateswara Reddy, E., Siva Naga Dhipti, G., Swathi, B. (2023). An Effective Automatic Facial Expression Recognition System Using Deep Neural Networks. In: Reddy, V.S., Prasad, V.K., Wang, J., Reddy, K.T.V. (eds) Soft Computing and Signal Processing. ICSCSP 2022. Smart Innovation, Systems and Technologies, vol 313. Springer, Singapore
A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” Proc. ICLR, 2021.
I. Giakoumis, N. Nikolaidis, and I. Pitas, “Digital restoration of old photographs,” Pattern Recognit., vol. 35, no. 6, pp. 1361–1371, 2002.
F. Stanco, L. Tenze, and A. Bimbo, “Digital inpainting of ancient frescoes,” J. Cultural Heritage, vol. 11, no. 4, pp. 408–419, 2010.
GS Naveen Kumar, VSK Reddy, “An efficient approach for video retrieval by spatio-temporal features”, International Journal of Knowledge-Based and Intelligent Engineering Systems, IOS Press, Vol. 23, Issue 4, ISSN: 1327-2314.
Y. Zhang, H. Zhang, and Q. Chen, “Image inpainting for cultural heritage restoration using GANs,” Proc. ICIP, pp. 466–470, 2020.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
