Research Articles

Research on Deep Learning-based Digital Restoration Method for Images of Intangible Cultural Heritage Thangka

Jianling Li1, Qiong Sun1*
1 School of Management, Beijing Union University, Beijing, China
Advance Online Publication
Research Articles
DOI https://doi.org/10.68791/acdm2026002
Published online: 2026-11-02 Received: 2026-09-10 Accepted: 2026-10-27

Download Citation

Current format Advance Online Publication
RIS BibTeX
pdf

Keywords

Thangka image
generative adversarial network
U-Net
image restoration

How to Cite

Li, J., & Sun, Q. (2026). Research on Deep Learning-based Digital Restoration Method for Images of Intangible Cultural Heritage Thangka. Arts, Communication & Digital Media. https://doi.org/10.68791/acdm2026002
ABNT ACM ACS AMA APA Chicago Harvard IEEE MLA Turabian Vancouver

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX
Share this article: Copy Link X LinkedIn Email

Citing this article

This article is published as an Advance Online Publication. Volume, issue and page numbers will be assigned once it is included in a printed issue. Please cite it as:

Arts, Communication & Digital Media, advance online publication, 2026-11-02, DOI: 10.68791/acdm2026002

Compliance & Registration

Abstract

Thangka is part of China’s intangible cultural heritage, but many Thangka images have certain defects due to problems such as age and improper preservation. This paper addressed the problem of digital restoration of Thangka images. Based on the generative adversarial network (GAN) in deep learning, a method was designed with U-Net as the generative model and PatchGAN as the discriminative model. The loss function of the model was composed of reconstruction loss, perceptual loss, and adversarial loss. Thangka images were collected to establish a dataset to verify the proposed approach. The results showed that at a mask ratio of 1%-10%, the peak signal-to-noise ratio, structural similarity index, and learned perceptual image patch similarity of the proposed approach were 33.21 dB, 0.9825, and 0.0187, and its performance was superior to that of methods such as EdgeConnect and progressive reconstruction of visual structure network at different mask ratios. The findings demonstrate the reliability of the proposed approach for digital restoration of images. It can be applied to the digital restoration of actual Thangka images.

DOI https://doi.org/10.68791/acdm2026002
pdf

References

  1. Yang, S. Safeguarding and inheriting intangible cultural heritage music in the Chongqing Three Gorges Reservoir area: A case study on Lore. Curator, 2025, 68(1), 125-140.
  2. Ding, F.; Ding, B.; Bai, Y.; Zhang, J. Emotional Drain in Digital Design for Inheritance of Intangible Cultural Heritage. E3S Web of Conferences,2021, 236, 05029.
  3. Liu, X.; Wang, T.; Taylor, M. Intangible Cultural Heritage Digital Protection System Based on Parallel Processing of Hardware and Software. The International Conference on Cyber Security Intelligence and Analytics, 2022.
  4. Wen, W.; Wang, X.; Ye Z. Protection and immersive experience of cultural heritage in the digital age: Technological empowerment, spatial reproduction, and future risks. Arts & Communication, 2025, 3(4),025040005.
  5. Gu, B. K. Digital Solutions for Cultural Heritage Protection: Korea's ODA Contributions to the BIMP-EAGA. SUVANNABHUMI, 2025, 17(1),33-52.
  6. Song, C.; Liu, L.; Wang, Z. Digital modeling of urban cultural space and research on cultural heritage protection method. Journal of Computational Methods in Sciences and Engineering, 2025, 25(6).
  7. Shen, Z.; Xu, Q.; Wang, M.; Xue Y. Application and Exploration of Computer Technology in Digital Protection of Bashu Intangible Cultural Heritage. 2024 5th International Conference on Information Science, Parallel and Distributed Systems (ISPDS), 2024, 492-497.
  8. Wu, J.; Guo, L.; Jiang, J.; Sun, Y. The Digital Protection and Practice of Intangible Cultural Heritage Crafts in the context of New Technology. E3S Web of Conferences, 2021, 236, 05024.
  9. Zhong, P.; Hu, W.; Zhao, Y.; Zhang, F. Geo-TCAM: a Thangka captioning method integrating topic modeling with geometry-guided spatial attention. npj Heritage Science, 2026, 14(1), 1-18.
  10. Shang, X. P. Research on Lingnan Culture Image Restoration Methods Based on Multi-Scale Non-Local Self-Similar Learning. IEEE Access, 2025, 13, 101639-101646.
  11. Dalal, H. N.; Patel, H. K.; Prajapati, N. K.; Shyal, N. M. Image Restoration Using Convolutional Neural Network-Di Strategy Bobcat Optimization Algorithm. International Journal of Intelligent Engineering & Systems, 2025, 18(5), 690.
  12. Sirikongtham, P.; Nimkoompai, A. Enhancing the Scanability of Damaged QR Codes Through Image Restoration Using GANs Combined with the Spectral Normalization Technique. International Journal of Advanced Computer Science & Applications, 2025, 16(10),638.
  13. Abtahi, M.; Majidinia, S.; Mansourzadeh, M.; Zarch, S.H.H.; Asadi, G.; Noghani, Y.T.; Shakiba, M.R.; Saeedi, A.; Yousefi, S. Enhancing diagnostic quality in dental bitewings using transformer and GAN-Based image restoration. Oral Radiology, 2026, 42(3), 625-634.
  14. Han, X.; Yang, H.; Xie, C. DHTCformer: A dynamic hybrid transformer-CNN for weather-degraded remote sensing image restoration. Signal, Image and Video Processing, 2026, 20(8), 475.
  15. Pandey, A.; Trehan, J.; Ram, P. K.; Singh, S. Comparative Analysis of Loss Functions in BigGAN for Medical Image Synthesis: A Case Study on Brain MRI Scans. 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), 2025.
  16. Li, H.; Wang, N.; Fang, J.; Jia, Y.; Ji, L.; Chen, X. Anime Sketch Coloring Based onSelf-attention Gate andProgressive PatchGAN. 2023 Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024, 237-249.
  17. Zhang, Y.; Nie, B.; Gao, Y. Robust Locomotion Policy With Adaptive Lipschitz Constraint for Legged Robots. IEEE Robotics and Automation Letters, 2025, 10(1), 272-279.
  18. Paul, H.; Udayangani, H.; Umesha, K.; Lankasena, N.; Liyanage, C.; Thambugala, K. Maize leaf disease detection using convolutional neural network: a mobile application based on pre-trained VGG16 architecture. New Zealand Journal of Crop and Horticultural Science, 2024, 53(2), 367-383.
  19. Liu, G.; Reda, F. A.; Shih, K. J.; Wang, T. C.; Tao, A.; Catanzaro, B. Image Inpainting for Irregular Holes Using Partial Convolutions. 15th European Conference on Computer Vision, 2018, 89-105.
  20. Nazeri, K.; Ng, E.; Joseph, T.; Qureshi, F.; Ebrahimi, M. EdgeConnect: Structure Guided Image Inpainting using Edge Prediction. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, 3265-3274.
  21. Li, J.; He, F.; Zhang, L.; Du, B.; Tao, D. Progressive Reconstruction of Visual Structure for Image Inpainting. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, 5961-5970.
  22. Zhu, M.; He, D.; Li, X.; Li, C.; Li, F.; Liu, X. Image Inpainting by End-to-End Cascaded Refinement With Mask Awareness. IEEE Transactions on Image Processing, 2021, 30, 4855-4866.
  23. Zeng, Y.; Fu, J.; Chao, H.; Guo, B. Aggregated Contextual Transformations for High-Resolution Image Inpainting. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(7), 3266-3280.
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2026 Jianling Li, Qiong Sun (Author)

Most read articles by the same author(s)