ARTIFICIAL INTELLIGENCE–ASSISTED DIGITAL RECONSTRUCTION FOR HERITAGE CONSERVATION: A STUDY OF MONUMENT RESTORATION
South India represents one of the most culturally and architecturally rich regions in the world, hosting a wide array of UNESCO World Heritage Sites and historically significant monuments. The Indian subcontinent has multiple archaeological sites as well as historical monuments in different states of ruin. While conventional restoration techniques are in use at various locations but the process still needs more focus and improved methods leveraging technology for expediting the initiative. Many of the heritage structures have undergone degradation due to aging, weather and human intervention particularly in culturally rich regions of Southern India. This study explores the application of Artificial Intelligence (AI) in the restoration of these monuments and artifacts through digital techniques by augmentation of damaged or lost architectural elements of heritage structures. The research investigates how machine learning, computer vision, and generative AI models can analyze historical images, maps, and archival records to recreate missing architectural features with improved accuracy and efficiency. Using AI-based image reconstruction and 3D modeling tools, digital models are generated and compared with traditional archaeological drawings and expert interpretations to evaluate reliability and authenticity. The study aims to assess whether AI can predict original architectural styles and reduce subjectivity in reconstruction processes. By providing a non-invasive and sustainable approach to heritage conservation, AI-assisted digital reconstruction offers new possibilities for documentation, visualization, and educational engagement. The findings contribute to interdisciplinary research integrating artificial intelligence with archaeology and cultural heritage preservation, highlighting AI’s potential as a supportive tool for future conservation practices in Southern India. We will take detailed case studies and explore step by step on the specific problem statement, the feasible remedial measures and an elaborate approach for optimum restoration of the heritage structure and artifacts
Uchil, C. (2026). Artificial Intelligence–Assisted Digital Reconstruction for Heritage Conservation: A Study of Monument Restoration. International Journal of Science, Strategic Management and Technology, 02(05). https://doi.org/10.55041/ijsmt.v2i4.347
Uchil, Chaithra.. "Artificial Intelligence–Assisted Digital Reconstruction for Heritage Conservation: A Study of Monument Restoration." International Journal of Science, Strategic Management and Technology, vol. 02, no. 05, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i4.347.
Uchil, Chaithra.. "Artificial Intelligence–Assisted Digital Reconstruction for Heritage Conservation: A Study of Monument Restoration." International Journal of Science, Strategic Management and Technology 02, no. 05 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i4.347.
2.Ye, Sifan, Wu, Ting, Jarvis, Michael, & Zhu, Yuhao (2020). Digital Reconstruction of Elmina Castle for Mobile Virtual Reality via Point-based Detail Transfer. https://arxiv.org/pdf/2012.10739v3 https://arxiv.org/pdf/2012.10739v3
3.Mikkelstrup, Anders Faarbæk, & Kristiansen, Morten (2023). Integrated Digital Reconstruction of Welded Components: Supporting Improved Fatigue Life Prediction. https://arxiv.org/pdf/2307.15604v1 https://arxiv.org/pdf/2307.15604v1
4.Goyal, Aryan, Mittal, Ashish, Rao, Pranav, Tadepalli, Manoj, & Putha, Preetham (2026). DiffusionXRay: A Diffusion and GAN-Based Approach for Enhancing Digitally Reconstructed Chest Radiographs. Data Engineering in Medical Imaging: Third MICCAI Workshop, DEMI 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 27, 2025, Proceedings. https://doi.org/10.1007/978-3-032-08009-7_4 https://doi.org/10.1007/978-3-032- 08009-7_4
5.Zhang, Pengyi, Zhong, Yunxin, Deng, Yulin, Tang, Xiaoying, & Li, Xiaoqiong (2020). DRR4Covid: Learning Automated COVID-19 Infection Segmentation from Digitally ReconstructedRadiographs. https://arxiv.org/pdf/2008.11478v1 https://arxiv.org/pdf/2008.11478v1
6.Gopalakrishnan, Vivek, & Golland, Polina (2022). Fast Auto-Differentiable Digitally Reconstructed Radiographs for Solving Inverse Problems in Intraoperative Imaging. https://arxiv.org/pdf/2208.12737v1 https://arxiv.org/pdf/2208.12737v1