Application of GANs in Ancient Architectural Heritage Image Restoration
Source abstract
Abstract
Han-Tang Western Region beacon towers hold significant historical value but suffer severe damage, with traditional restoration lacking visual references. This paper proposes a GAN-based image restoration method combining Pix2Pix and CycleGAN models. Experiments show Pix2Pix achieves higher accuracy but requires paired samples. We design a hybrid workflow: CycleGAN first generates restoration targets, then concatenates with original images for Pix2Pix input. AI-generated virtual beacon images enhance database diversity, significantly improving restoration stability and accuracy. This research innovatively applies deep learning to architectural heritage preservation, providing a feasible method for building image restoration with limited data. It efficiently supplies visual references for traditional restoration and offers a scalable technical pathway for beacon tower virtual reconstruction, providing valuable guidance for preservation work.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Generative Adversarial Networks and Image Synthesis · 3D Surveying and Cultural Heritage · Image Processing and 3D Reconstruction
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (27)
Show source-provided references
1. Borri, A. & Corradi, M. Architectural heritage: a discussion on conservation and safety. Heritage 2, 631–647 (2019).10.3390/heritage2010041 ↗
2. Zhou, W., Song, S. & Feng, K. The sustainability cycle of historic houses and cultural memory: controversy between historic preservation and heritage conservation. Front. Archit. Res. 11, 1030–1046 (2022).10.1016/j.foar.2022.04.006 ↗
3. Maiwald, F. et al. Photogrammetric analysis of historical image repositories for virtual reconstruction in the field of digital humanities. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 42, 447–452 (2017).10.5194/isprs-archives-XLII-2-W3-447-2017 ↗
4. Pietroni, E. & Ferdani, D. Virtual restoration and virtual reconstruction in cultural heritage: terminology, methodologies, visual representation techniques and cognitive models. Information 12, 167 (2021).10.3390/info12040167 ↗
5. Cardilicchio, A. et al. Assessing the user experience in realistic virtual reality environment: operational framework and experimental survey. Procedia Comput. Sci. 253, 1810–1819 (2025).10.1016/j.procs.2025.01.243 ↗
6. Zhang, X., Zhi, Y., Xu, J. & Han, L. Digital protection and utilization of architectural heritage using knowledge visualization. Buildings 12, 1604 (2022).10.3390/buildings12101604 ↗
7. Lian, Y. & Xie, J. The evolution of digital cultural heritage research: identifying key trends, hotspots, and challenges through bibliometric analysis. Sustainability 16, 7125 (2024).10.3390/su16167125 ↗
8. Gervasi, O., Perri, D., Simonetti, M. & Tasso, S. Strategies for the digitalization of cultural heritage. In Computational Science and Its Applications – ICCSA 2022 486–502 (Springer, Cham, 2022).10.1007/978-3-031-10592-0_35 ↗
9. Santagati, C., Inzerillo, L. & Di Paola, F. Image-based modeling techniques for architectural heritage 3D digitalization: limits and potentialities. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 40, 555–560 (2013).10.5194/isprsarchives-XL-5-W2-555-2013 ↗
10. Xu, H.-J. Summary on the review of the investigation of the Great Wall in China. J. Hebei GEO Univ. 41, 123–132 (2018).
11. Zhao, C. Military relics of the Silk Road from the perspective of archaeology. Wenwu. 2, 73–80 (2016).
12. Ma, D. History of China’s Borderland Strategy (Zhongzhou Ancient Books Publishing House, Zhengzhou, China, 2000).
13. Jiang, N. Research on the Border Defense System of Han Dynasty (Central China Normal University Press, Wuhan, China, 2013).
14. Wu, J. & Liu, Q. A study on the development of garrison reclamation along the Silk Road under the management strategy of the Western Regions in the Han dynasties. Xiyu Yanjiu (The Western Regions Studies) 124, 10–16 (2021).
15. Yang, Y., Zhang, Y. & Li, Y. Temporal and spatial distribution characteristics of the Ming Great Wall. Herit. Sci. 12, 81 (2024).10.1186/s40494-024-01198-1 ↗
16. Zhang, S. et al. Spatial pattern and influencing factors of land border cultural heritage in China. Herit. Sci. 11, 187 (2023).10.1186/s40494-023-01037-9 ↗
17. Li, X. Determination of the temporal–spatial distribution patterns of ancient heritage sites in China and their influencing factors via GIS. Herit. Sci. 12, 143 (2024).10.1186/s40494-024-01258-6 ↗
18. Zhang, J. et al. ArchGPT: harnessing large language models for supporting renovation and conservation of traditional architectural heritage. Herit. Sci. 12, 220 (2024).10.1186/s40494-024-01334-x ↗
19. Thrun, S., Saul, L. & Schölkopf, B. Advances in neural information processing systems 16. In Proc. NeurIPS 2003 47–110 (MIT Press, London, UK, 2004).
20. Isola, P., Zhu, J. Y., Zhou, T. & Efros, A. A. Image-to-image translation with conditional adversarial networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 1125–1134 (IEEE, 2017).10.1109/CVPR.2017.632 ↗
21. Altaweel, M., Khelifi, A. & Zafar, M. H. Using generative AI for reconstructing cultural artifacts: examples using Roman coins. J. Comput. Appl. Archaeol. 7, 301–315 (2024).
22. Zhao, F. et al. GAN-based heterogeneous network for ancient mural restoration. Herit. Sci. 12, 418 (2024).10.1186/s40494-024-01517-6 ↗
23. Liu, S. B. et al. Deep learning enables parallel camera with enhanced-resolution and computational zoom imaging. PhotoniX. 4, 17 (2023).10.1186/s43074-023-00095-3 ↗
24. Ali, A. & Lee, O. J. Facade style mixing using artificial intelligence for urban infill. Architecture 3, 258–269 (2023).10.3390/architecture3020015 ↗
25. Chai, P. et al. Generative adversarial networks in construction applications. Autom. Constr. 159, 105265 (2024).10.1016/j.autcon.2024.105265 ↗
26. Meng, S. Exploring in the latent space of design: a method of plausible building facade image generation, property control, and model explanation based on StyleGAN2. In Proc. 3rd International Conference on Computational Design and Robotic Fabrication (DigitalFUTURES 2021) 3 (Springer, Singapore, 2022).10.1007/978-981-16-5983-6_6 ↗
27. Yu, Q., Malaeb, J. & Ma, W. Architectural facade recognition and generation through generative adversarial networks. In Proc. 2020 International Conference on Big Data, Artificial Intelligence, and Software Engineering (ICBASE) 310–316 (IEEE, 2020).10.1109/ICBASE51474.2020.00072 ↗