基于投影流网络和嵌入空间损失的纹样风格迁移  

Pattern style transfer based on projection flow networks and embedding space loss

作　　者：朱昱儒 侯珏 杨阳[1,2] 刘正[2,3] ZHU Yuru;HOU Jue;YANG Yang;LIU Zheng(School of Fashion Design&Engineering,Zhejiang Sci-Tech University,Hangzhou 311199,China;Key Laboratory of Silk Cultural Heritage and Product Design Digital Technology,Ministry of Culture and Tourism,Zhejiang Sci-Tech University,Hangzhou 311199,China;Zhejiang International Institute of Fashion Technology,Zhejiang Sci-Tech University,Hangzhou 311199,China)

机构地区：[1]浙江理工大学服装学院,杭州311199 [2]浙江理工大学丝绸文化传承与产品设计数字化技术文旅部重点实验室,杭州311199 [3]浙江理工大学国际时装技术学院,杭州311199

出　　处：《浙江理工大学学报(自然科学版)》2025年第2期237-245,共9页Journal of Zhejiang Sci-Tech University(Natural Sciences)

基　　金：文化和旅游部重点实验室资助项目(23072247-N)。

摘　　要：针对编解码器框架造成的图像重建误差、恢复偏差以及图像风格迁移方法存在内容泄露和局部伪影等亟待解决的问题,提出了一种基于投影流网络以及嵌入空间损失的纹样风格迁移模型。通过融合投影流网络与矢量量化变分自编码器实现无偏风格迁移,并对风格特征进行精细编码和匹配,保留更完整图像内容细节,且捕获关键风格特征;设计了一种计算风格化图和风格图的嵌入空间损失,融入总体损失函数以保证风格特征的均匀分布,减少风格差异;以云锦为例进行织物纹样风格的创新设计。结果表明:基于投影流网络和嵌入空间损失的纹样风格迁移的迁移效果,在内容评价指标结构相似性(Structural similarity,SSIM)、内容损失上的分值较对比模型分别提高86.21%、54.29%、20%和32.58%、18.68%、18.99%;风格评价指标Gram损失为4.5×10^(-6),较对比模型提高近一倍,表明该方法有效平衡了内容保留与风格迁移的需求,提高风格化效果。该模型在改善内容泄漏的同时避免了内容失真和风格过度覆盖,有效捕捉复杂风格特征和色彩层次,促进纹样创新设计,增加风格迁移在纺织服装领域的可能性。Aiming at the problems that need to be solved urgently,such as image reconstruction error,recovery biases caused by coded framework,and content leak and local artifacts during the style transfer process,a pattern style transfer model based on projection flow network and embedded space loss was proposed.Firstly,by integrating the projection flow network with the vector quantized-variational autoencoder,unbiased style transfer was realized,and style features were finely coded and matched to retain more complete image content details and capture key style features.Then,a method was designed to calculate the embedded space loss of stylized graph and style graph,and the overall loss function was incorporated to ensure the uniform distribution of style features and reduce style differences.With Yunjin brocade as an example,the innovative design of fabric pattern style was carried out.The results showed that the transfer effect of pattern style transfer based on projection flow network and embedded space loss scored higher by 86.21%,54.29%and 20%,and 32.58%,18.68%and 18.99%,respectively in terms of the content evaluation metrics of structural similarity(SSIM),and content loss compared to the comparison models;with a Gram loss of 4.5×10^(-6),the model nearly doubled the performance of comparative models,indicating that this method effectively balanced the needs of content retention and style transfer and improved the stylization effect.The model improves content leak while avoiding content distortion and style over-coverage,effectively captures complex style features and color hierarchies,facilitates innovative design of patterns,and increases the possibility of style transfer in the textile and apparel field.

关 键 词：风格迁移 嵌入空间损失 矢量量化变分自编码器 内容泄漏 投影流 纹样 

分 类 号：TS941.26[轻工技术与工程—服装设计与工程]