[1]刘贝芬,冯峥嵘,张坦坦.基于风格迁移算法的印花图案数字化设计[J].服装学报,2025,10(06):530-535.
　LIU Beifen,FENG Zhengrong,ZHANG Tantan.Digital Design of Printed Patterns Based on Style Transfer Algorithm[J].Journal of Clothing Research,2025,10(06):530-535.
点击复制

基于风格迁移算法的印花图案数字化设计()

《服装学报》[ISSN:2096-1928/CN:32-1864/TS]

卷:
第10卷
期数:
2025年06期
页码:
530-535
栏目:
服装设计
出版日期:
2025-12-30

文章信息/Info

Title:
Digital Design of Printed Patterns Based on Style Transfer Algorithm
作者:
刘贝芬1;  冯峥嵘2;  张坦坦2
1.安徽工程大学 纺织服装学院,安徽 芜湖 241000; 2.安徽工程大学 高端装备先进感知与智能控制教育部重点实验室,安徽 芜湖 241000
Author(s):
LIU Beifen1;  FENG Zhengrong2;  ZHANG Tantan2
1. School of Textile and Garment, Anhui Polytechnic University, Wuhu 241000,China; 2. Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu 241000,China
分类号:
TS 941.2
文献标志码:
A
摘要:
针对印花图案设计风格多样性与个性化需求,采用一种基于多源特征提取的印花图案数字化设计方法提取素材图案的轮廓线稿,通过AFEM模块增强内容图案轮廓线的注意力,在风格感知解码器中引入缩放点积注意力机制,得到改进后的风格迁移模型MFEST,并探讨其在产品设计应用中的可行性。研究表明,优化后的 MFEST模型在艺术评价指标和技术评价指标测评中均表现较佳,能够保留素材图案的构图内容、层次感以及风格图的艺术特征,有效解决印花图案边缘色彩混乱和细节丢失的问题,为印花面料设计提供智能化解决方案。
Abstract:
Aiming at the diversity of design styles and personalized demands for printed patterns, this study proposes a digital design method for printed patterns based on multi-source feature extraction. First, the contour line drafts of material patterns are extracted; then, the AFEM module is employed to enhance the attention on the contour lines of content patterns; subsequently, the scaled dot-product attention mechanism is introduced into the style-aware decoder to develop an improved style transfer model, namely MFEST. Finally, the feasibility of its application in product design is discussed. Experimental results indicate that the optimized MFEST model achieves superior performance in both artistic and technical evaluation metrics. It can effectively preserve the compositional content, hierarchical structure of material patterns, and the artistic characteristics of style images, while addressing the issues of edge color confusion and detail loss in printed patterns. This research provides an intelligent solution for the design of printed fabrics.

参考文献/References:

[1] 石文慧, 朱海峰, 蒋汶秦, 等. 传统纺织品图案的屈曲矫正与再生设计[J]. 服装学报, 2025, 10(1): 40- 45.
SHI Wenhui, ZHU Haifeng, JIANG Wenqin, et al. Curvature correction and regenerative design of traditional textile patterns[J]. Journal of Clothing Research, 2025, 10(1): 40- 45.(in Chinese)
[2] 杨雪, 陈可欣. Midjourney在纺织服装设计中的探索与应用[J]. 服装学报, 2024, 9(6): 549-555.
YANG Xue, CHEN Kexin. Exploration and application of midj-ourney in textile and fashion design[J]. Journal of Clothing Research, 2024, 9(6): 549-555.(in Chinese)
[3] 孟媚, 吴艳, 孔旭, 等. 参数化形状文法在传统图案设计中的应用[J]. 毛纺科技, 2024, 52(11): 76-84.
MENG Mei, WU Yan, KONG Xu, et al. Application of parametric shape grammar in textile pattern design[J]. Wool Textile Journal, 2024, 52(11): 76-84.(in Chinese)
[4] 程鹏飞, 王伟珍, 房媛. 基于卷积神经网络的风格迁移泳装图案设计[J]. 丝绸, 2023, 60(3): 97-104.
CHENG Pengfei, WANG Weizhen, FANG Yuan. Design of style transfer swimsuit patterns based on convolutional neural network[J]. Journal of Silk, 2023, 60(3): 97-104.(in Chinese)
[5] MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. arXiv,2014:1411-1784.
[6] HO J, JAIN A, ABBEEL P. Denoising diffusion probabilistic models[J]. Advances in Neural Information Processing Systems, 2020, 33: 11239.
[7] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30: 5998- 6008.
[8] 侯宇康, 吕健, 刘翔, 等. 基于神经风格迁移网络的民族图案创新方法[J]. 图学学报, 2020, 41(4): 606- 613.
HOU Yukang, LV Jian, LIU Xiang, et al. Innovative method of ethnic pattern based on neural style transfer network[J]. Journal of Graphics, 2020, 41(4): 606- 613.(in Chinese)
[9] 冉二飞, 贾小军, 喻擎苍, 等. 基于SE注意力CycleGAN的蓝印花布单纹样自动生成[J]. 丝绸, 2024, 61(1): 31-37.
RAN Erfei, JIA Xiaojun, YU Qingcang, et al. Single pattern automatic generation of blue calico based on SE attention CycleGAN[J]. Journal of Silk, 2024, 61(1): 31-37.(in Chinese)
[10] 李莉, 毛子晗, 吕思奇, 等. GAN与Diffusion在传统纹样设计中的实验研究[J]. 丝绸, 2024, 61(8): 9-22.
LI Li, MAO Zihan, Lü Siqi, et al. An experimental study on the application of GAN and Diffusion models in traditional pattern design[J]. Journal of Silk, 2024, 61(8): 9-22.(in Chinese)
[11] 张佳伟, 李华军, 王秀丽, 等. 基于扩散模型的印花图案生成方法设计[J]. 计算机测量与控制, 2024, 32(10): 243-249.
ZHANG Jiawei, LI Huajun, WANG Xiuli, et al. Design of printed pattern generation method based on diffusion models[J]. Computer Measurement and Control, 2024, 32(10): 243-249.(in Chinese)
[12] 姚琳涵, 张颖, 姚岚, 等. 基于多尺度纹理合成的刺绣风格迁移模型[J]. 纺织学报, 2023, 44(9): 84-90.
YAO Linhan, ZHANG Ying, YAO Lan, et al. Embroidery style transfer modeling based on multi-scale texture synthesis[J]. Journal of Textile Research, 2023, 44(9): 84-90.(in Chinese)
[13] 亚历克斯·罗素.纺织品印花图案设计[M]. 北京:中国纺织出版社 2015.
[14] 欧文·琼斯.中国纹样.[M]. 北京: 人民文学出版社, 2021.
[15] 三采文化. 中国风纹样1007萃炼中国千年传统美学成就之菁华[M]. 台北: 三采文化出版事业有限公司, 2009.
[16] 三采文化. 北欧设计纹样1003[M]. 台北: 三采文化出版事业有限公司, 2009.
[17] 伊丽莎白·威尔海德. 世界花纹与图案大典[M]. 张心童,译.北京: 中国画报出版社, 2020.
[18] 王美艳. 艺术批评学[M]. 北京: 北京大学出版社, 2011: 171-173.
[19] 黄厚石. 新编设计批评[M]. 南京: 东南大学出版社, 2022: 207-208.
[20] WANG J B, YANG H, FU J L, et al. Fine-grained image style transfer withVisual transformers[C]//Computer Vision-ACCV 2022. Cham: Springer, 2023: 427- 443.
[21] LI YIJUN, FANG CHEN, YANG JIMEI, et al. Universal style transfer via feature transforms[J]. Advances in neural information processing systems, 2017, 30: 386-396.
[22] ZHANG C Y, XU X G, WANG L, et al. S2WAT: image style transfer via hierarchical vision transformer using strips window attention[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(7): 7024-7032.
[23] LIU S H, LIN T W, HE D L, et al. AdaAttN: revisit attention mechanism in arbitrary neural style transfer[C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV).Canada:IEEE, 2021: 6629- 6638.
(责任编辑:张 雪)

更新日期/Last Update: 2025-12-30