全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
Design  2023 

基于StyleGAN2的柯尔克孜族纹样的生成研究
Research on the Generation of Kirgiz Patterns Based on StyleGAN2

DOI: 10.12677/Design.2023.83215, PP. 1785-1795

Keywords: 柯尔克孜族纹样,生成式对抗网络,GAN,纹样创新生成
Kirgiz Patterns
, Generative Adversarial Network, GAN, Pattern Innovation Generation

Full-Text   Cite this paper   Add to My Lib

Abstract:

探究柯尔克孜民族纹样的创新生成方法,在民族优秀传统文化传播方面进行尝试。通过技术方法的创新促进民族纹样与现代时尚元素的结合,加快民族纹样的现代化应用。将收集到的柯尔克孜族图案导入到模型系统中,并运用生成式对抗网络技术对模型进行训练,使其衍生出新的纹样元素,建立柯尔克孜族纹样元素库。在实验样本有限的情况下,得到了柯尔克孜族创新性纹样,丰富了柯尔克孜族纹样元素库,为进一步探索更可控的纹样生成技术奠定了基础。运用生成式对抗网络模型计算得到的柯尔克孜族纹样元素,既有传统纹样的艺术性,也满足了信息时代艺术设计衍生的时效性需求,更与现代时尚追求偏好相一致。通过在现代文创产品和服装服饰等设计中的应用,促进了优秀民族文化的传播和继承。
The objection of this study is to explore the innovative generation method of Kirgiz ethnic pattern and attempt to apply it into diffusion of the excellent traditional culture of the nation, promote the combination of ethnic patterns and modern fashion elements through the innovation of technical methods, and accelerate the modern application of ethnic patterns. The collected Kirgiz patterns were imported into the model system, and the model was trained using generative adversarial network technology to derive new pattern elements and establish a Kirgiz pattern element library. In the case of limited experimental samples, the innovative patterns of Kirgiz were obtained, and the pattern element library of Kirgiz was enriched, which is favorable for further exploration of more controllable pattern generation techniques. The Kirgiz ethnic pattern elements calculated using the generative adversarial network model not only have the artistry of traditional patterns, but also meet the timeliness requirements of derivation of art and design at information age, and are consistent with the contemporary preferences for fashion pursuit. Through its application in modern cultural and creative products and clothing design, the study has promoted the dissemination and inheritance of excellent ethnic culture.

References

[1]  新华社. 中共中央办公厅 国务院办公厅印发《关于推进实施国家文化数字化战略的意见》[EB/OL]. https://www.gov.cn/xinwen/2022-05/22/content_5691759.htm?eqid=ca6bbf9a0001492900000006647602bc, 2022-05-22.
[2]  周曼, 信晓瑜, 张辉, 等. 柯尔克孜族花毡图案在线设计系统开发[J]. 毛纺科技, 2022, 50(9): 61-66.
[3]  米高峰, 王少杰. 中华传统文化传承与国产动画艺术传播[J]. 青年记者, 2018(11): 76-77.
[4]  毛新康, 米高峰. AI赋能数字媒体艺术的发展与思考[J]. 媒体融合新观察, 2021(1): 58-60.
[5]  易苗苗. 中国柯尔克孜民族装饰纹样艺术的文化解析[J]. 染整技术, 2018, 40(6): 48-51.
[6]  阿地里?居玛吐尔地. 中国柯尔克孜族[M]. 银川: 宁夏人民出版社, 2012.
[7]  罗娇. 柯尔克孜族刺绣纹样的特征及创新应用[D]: [硕士学位论文]. 无锡: 江南大学, 2021.
[8]  潘云鹤. 智能CAD方法与模型[M]. 北京: 科学出版社, 1997.
[9]  黄琦, 孙守迁. 产品风格计算研究进展[J]. 计算机辅助设计与图形学学报, 2006, 18(11): 1629-1636.
[10]  秦臻, 季铁, 刘芳, 等. 基于民族图案基元可拓语义的产品设计方法[J]. 计算机辅助设计与图形学学报, 2021, 33(10): 1595-1603.
[11]  Goodfellow, J., Abadie, J.P., Mirza, M., et al. (2014) Generative Adversarial Networks. arXiv: 1406.2661. https://arxiv.org/abs/1406.2661
[12]  刘淼, 王晨月. GAN技术在传统竹编元素生成中的设计[J]. 包装工程, 2020, 41(20): 34-40.
[13]  邓正根, 吕健, 王帅, 等. 基于StyleGAN的草图生成产品设计效果图方法研究[J/OL]. 包装工程: 1-10. http://kns.cnki.net/kcms/detail/50.1094.tb.20220816.0837.002.html, 2023-03-27.
[14]  何文泽. 基于生成式对抗网络的民族图案生成研究[D]: [硕士学位论文]. 长春: 吉林大学, 2022.
[15]  董荪, 丁友东, 钱昀. 基于人工智能的风格迁移算法在动画特效设计中的应用[J]. 装饰, 2018(1): 104-107.
[16]  陈捷, 徐戈. 风格迁移算法在漆艺文创品设计中的运用[J]. 装饰, 2020(3): 82-85.
[17]  Karras, T., Laine, S. and Aila, T. (2019) A Style-Based Generator Architecture for Generative Adversarial Networks. Proceedings of the IEEE/CVF Conference on Com-puter Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 4396-4405.
https://doi.org/10.1109/CVPR.2019.00453
[18]  Karras, T., Laine, S., Aittala, M., et al. (2020) Analyzing and Improving the Image Quality of StyleGAN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 8107-8116.
https://doi.org/10.1109/CVPR42600.2020.00813
[19]  Karras, T., Aittala, M., Hellsten, J., et al. (2020) Training Generative Adversarial Networks with Limited Data. Advances in Neural Information Processing Systems, 33, 12104-12114.
[20]  Radford, A., Kim, J.W., Hallacy, C., et al. (2021) Learning Transferable Visual Models from Natural Language Supervision. International Conference on Machine Learning, 18-24 July 2021, 8748-8763.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133