Research on the Innovation of Dunhuang Ceiling Patterns Using Deep Style Transfer Algorithms
This paper explores the effective integration of the traditional aesthetics of Dunhuang Ceiling Patterns with modern design based on deep style transfer algorithms. Through the analysis of traditional Ceiling Patterns, combined with deep learning technology, the paper achieves the stylistic transformation of traditional patterns and discusses their application paradigms in modern design. By combining deep learning technology with traditional aesthetics, the paper innovatively investigates the fusion of traditional culture and modern design, offering new perspectives and methods for modern design.
[1] Basheer, A. M., Jose, J., & Sajith, K. (2021). A faster neural algorithm for artistic style transfer. International Journal of Innovative Science, Engineering and Technology, 8(8), 458-468. https://ijiset.com/vol8/v8s8/IJISET_V8_I08_38.pdf
[2] Chen, T., & Xu, X. (2013). Traditional cultural elements in modern interior soft decoration design: an application study. Technology and Market, 20(11), 142-143.
[3] Dong, S., Ding, Y. D., & Qian, Y. (2018). Application of AI-based style transfer algorithm in animation special effects design. Decoration, (1), 104-107. http://wanfangdata.com.cn/details/detail.do?_type=perio&id=zhuangshi201801021
[4] Feng, G. W. (2019). Research on the application value of Dunhuang caisson patterns in modern design. Westleather, 41(16), 27-28.
[5] Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style [Preprint]. arXiv. https://doi.org/10.48550/arXiv.1508.06576
[6] Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In European conference on computer vision (pp. 694-711). Cham: Springer International Publishing.
[7] Lee, S. B., & Lee, Y. J. (2024). A study on the development of textile design using traditional Chinese bat patterns as a motif. Journal of Fashion Business, 28(3), 48-68. https://doi.org/10.12940/jfb.2024.28.3.48.
[8] Li, L., Qing, C., Tan, J., Jin, J., & Xu, X. (2025). Artistic style transfer via fine-grained text guidance and contrastive semantics similarity. IEEE Transactions on Multimedia, 27, 7570-7583. https://doi.org/10.1109/TMM.2025.3599050
[9] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition [Preprint]. arXiv. https://doi.org/10.48550/arXiv.1409.1556
[10] Wang, Q., Bai, X., Wang, H., Qin, Z., Chen, A., Li, H., Tang, X., & Hu, Y. (2024). InstantID: Zero-shot identity-preserving generation in seconds [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2401.07519
[11] Zhang, J. L. (2022). Application of music and dance images in Dunhuang frescoes in homestay environment design [Master's thesis, Lanzhou University of Technology]. https://doi.org/10.27206/d.cnki.ggsgu.2022.001118
[12] Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 2242-2251). https://doi.org/10.1109/ICCV.2017.244