AI-BASED RESTORATION OF ANCIENT SCULPTURES
DOI:
https://doi.org/10.29121/shodhkosh.v6.i5s.2025.6878Keywords:
AI Restoration, 3D Reconstruction, Cultural Heritage, Lidar Scanning, Digital Conservation Ethics, Multimodal Fusion, AR/VR Museum SystemsAbstract [English]
Recent conservation of old sculptures is still a primary reinforcement to cultural heritage conservation; it has traditionally been based on the hand process that is subjective, irreversible and time consuming. The paper introduces a framework of AI-based restoration which incorporates multimodal data gathering, hybrid neural model, and expert-guided verification to attain accurate and ethically controlled digital restoration. The system makes use of LiDAR, CT, photogrammetry as well as multispectral imaging to acquire geometric and material information, which is processed with the help of a hybrid CNN-GAN-Transformer pipeline. The CNN derives structural, textual features, the GAN recreates the geometry that is missing and the Transformer imposes stylistic consistency with the help of knowledge-driven cultural embeddings. The quantitative analyses of three case studies of Roman marble, Chinese terracotta and Indian sandstone sculptures show that the framework is robust with 2530% reduction in Chamfer and Hausdorff distances, mean SSIM = 0.94, and cultural authenticity of above 4.3/5 by panels. Qualitative tests also prove that the restored outputs are both geometrical and culturally faithful. The architectural design enables the implementation of interactive, reversible, and transparent restoration processes to support the implementation of large-scale deployment of the modular architecture in museums, digital repositories, and AR/VR heritage platforms. In addition to performance, the framework focuses on ethical design of AI based on the concepts of human-in-the-loop testing, diversification of dataset, and documentation with provenance in consideration. Findings confirm the importance of AI as a cooperative stakeholder in the preservation of sculptural heritage of humankind, as an integration of computational intelligence and cultural accountability.
References
Agrawal, K., Aggarwal, M., Tanwar, S., Sharma, G., Bokoro, P. N., and Sharma, R. (2022). An Extensive Blockchain-Based Applications Survey: Tools, Frameworks, Opportunities, Challenges, and Solutions. IEEE Access, 10, 116858–116906. https://doi.org/10.1109/ACCESS.2022.3218166 DOI: https://doi.org/10.1109/ACCESS.2022.3219160
Aoulalay, N., El Makhfi, N., Abounaima, M. C., and Massar, M. (2020). Classification of Moroccan Decorative Patterns Based on Machine Learning Algorithms. In Proceedings of the 2nd IEEE International Conference on Electronics, Control, Optimization, and Computer Science (ICECOCS), 1–7. Kenitra, Morocco. https://doi.org/10.1109/ICECOCS50124.2020.9314486 DOI: https://doi.org/10.1109/ICECOCS50124.2020.9314443
Argyrou, A., Agapiou, A., Papakonstantinou, A., and Alexakis, D. D. (2023). Comparison of Machine Learning Pixel-Based Classifiers for Detecting Archaeological Ceramics. Drones, 7, 578. https://doi.org/10.3390/drones7100578 DOI: https://doi.org/10.3390/drones7090578
Brumann, and Gfeller, A. É. (2022). Cultural Landscapes and the UNESCO World Heritage List: Perpetuating European Dominance. International Journal of Heritage Studies, 28, 147–162. https://doi.org/10.1080/13527258.2021.1999967 DOI: https://doi.org/10.1080/13527258.2021.1941197
Cardarelli, L. (2022). A Deep Variational Convolutional Autoencoder for Unsupervised Features Extraction of Ceramic Profiles: A Case Study from Central Italy. Journal of Archaeological Science, 144, 105640. https://doi.org/10.1016/j.jas.2022.105640 DOI: https://doi.org/10.1016/j.jas.2022.105640
Dieber, J., and Kirrane, S. (2022). A Novel Model Usability Evaluation Framework (MUsE) for Explainable Artificial Intelligence. Information Fusion, 81, 143–153. https://doi.org/10.1016/j.inffus.2021.12.012 DOI: https://doi.org/10.1016/j.inffus.2021.11.017
Doleżyńska-Sewerniak. (2019). Color of the Façades of Historic Buildings from the Turn of the 19th and 20th Centuries in Northeast Poland. Color Research and Application, 44, 139–149. https://doi.org/10.1002/col.22343 DOI: https://doi.org/10.1002/col.22276
Graham, P. (2014). Japanese Design : Art, Aesthetics and Culture. Tuttle Publishing.
Jaillant, L., Mitchell, O., Ewoh-Opu, E., and Hidalgo Urbaneja, M. (2025). How Can We Improve the Diversity of Archival Collections with AI? Opportunities, Risks, and Solutions. AI and Society, 40, 4447–4459. https://doi.org/10.1007/s00146-024-01870-4 DOI: https://doi.org/10.1007/s00146-025-02222-z
Khare, S. K., and Bajaj, V. (2021). Time-Frequency Representation and Convolutional Neural Network-Based Emotion Recognition. IEEE Transactions on Neural Networks and Learning Systems, 32, 2901–2909. https://doi.org/10.1109/TNNLS.2020.3001248 DOI: https://doi.org/10.1109/TNNLS.2020.3008938
Kuntitan, P., and Chaowalit, O. (2022). Using Deep Learning for the Image Recognition of Motifs on the Center of Sukhothai Ceramics. Current Applied Science and Technology, 22(2). https://doi.org/10.55003/cast.2022.02.22.002 DOI: https://doi.org/10.55003/cast.2022.02.22.002
Lavine, B., Almirall, J., Muehlethaler, C., Neumann, C., and Workman, J. (2020). Criteria for Comparing Infrared Spectra: A Review of the Forensic and Analytical Chemistry Literature. Forensic Chemistry, 18, 100224. https://doi.org/10.1016/j.forc.2020.100224 DOI: https://doi.org/10.1016/j.forc.2020.100224
Ma, J., Peng, Y., Cheng, W., Qiu, M., and Nie, Y. (2021). Identification Method of Ancient Céramies Révision. In Proceedings of the 8th IEEE International Conférence on Cyber Security and Cloud Computing (CSCloud) and the 7th IEEE International Conférence on Edge Computing and Scalable Cloud (EdgeCom), 213–218. Washington, DC, USA. DOI: https://doi.org/10.1109/CSCloud-EdgeCom52276.2021.00046
Mazzetto, S. (2024). Integrating Emerging Technologies with Digital Twins for Heritage Building Conservation: An Interdisciplinary Approach with Expert Insights and Bibliometric Analysis. Heritage, 7, 6432–6479. https://doi.org/10.3390/heritage7040309 DOI: https://doi.org/10.3390/heritage7110300
Poger, D., Yen, L., and Braet, F. (2023). Big Data in Contemporary Electron Microscopy: Challenges and Opportunities in Data Transfer, Compute, and Management. Histochemistry and Cell Biology, 160, 169–192. https://doi.org/10.1007/s00418-023-02208-1 DOI: https://doi.org/10.1007/s00418-023-02191-8
Rao, X., Wang, X., and Ming, Y. (2021). Ancient Ceramic Restoration Platform Based on Virtual Reality Technology. In Proceedings of the International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2021) (Vol. 12153, pp. 198–203). Sanya, China. https://doi.org/10.1007/978-3-030-90196-7_19 DOI: https://doi.org/10.1117/12.2626659
Skublewska-Paszkowska, M., Milosz, M., Powroznik, P., and Lukasik, E. (2022). 3D Technologies for Intangible Cultural Heritage Preservation: Literature Review for Selected Databases. Heritage, 10, 1–24. https://doi.org/10.3390/heritage10010001 DOI: https://doi.org/10.1186/s40494-021-00633-x
Spennemann, D. H. R. (2024). Generative Artificial Intelligence, Human Agency, and the Future of Cultural Heritage. Heritage, 7, 3597–3609. https://doi.org/10.3390/heritage7060187 DOI: https://doi.org/10.3390/heritage7070170
Utomo, S., et al. (2023). AIX Implementation in Image-Based PM2.5 Estimation: Toward an AI Model for Better Understanding. In Proceedings of the 15th International Conference on Knowledge and Smart Technology (KST), 1–6. Phuket, Thailand. https://doi.org/10.1109/KST57295.2023.10035789 DOI: https://doi.org/10.1109/KST57286.2023.10086917
Vassilev, H., Laska, M., and Blankenbach, J. (2024). Uncertainty-Aware Point Cloud Segmentation for Infrastructure Projects Using Bayesian Deep Learning. Automation in Construction, 164, 105419. https://doi.org/10.1016/j.autcon.2024.105419 DOI: https://doi.org/10.1016/j.autcon.2024.105419
Yu, T., et al. (2022). Artificial Intelligence for Dunhuang Cultural Heritage Protection: The Project and the Dataset. International Journal of Computer Vision, 130, 2646–2673. https://doi.org/10.1007/s11263-022-01657-8 DOI: https://doi.org/10.1007/s11263-022-01665-x
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Swarnima Singh, Mr. Abhinav Srivastav, Sulabh Mahajan, Mr. Debasish Das, Pooja Goel, Yamunadevi S, Bipin Sule
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
