首页 | 官方网站   微博 | 高级检索  
     

改进的CAGAN在虚拟试衣中的应用
引用本文:徐小春,董洪伟,魏程峰.改进的CAGAN在虚拟试衣中的应用[J].计算机工程与应用,2021,57(6):152-158.
作者姓名:徐小春  董洪伟  魏程峰
作者单位:江南大学 人工智能与计算机学院,江苏 无锡 214122
摘    要:针对CAGAN(Conditional Analogy GAN)换衣后效果模糊,在目标衣服与原始衣服长短不一致时效果一般,相对目标衣服保留过少的细节等问题做了相关研究并对CAGAN进行了改进,提出了新的虚拟试衣方式。经过改进的CAGAN生成一个粗糙的结果,由该结果得到目标衣服穿在模特身上改变形状后的mask,接下来利用mask对目标衣服进行变形,综合变形的衣服和第一步的结果便得到最终的试衣图像。实验结果表明,该方法解决了前面存在的问题,而且取得了非常好的效果。

关 键 词:生成式对抗网络  虚拟试衣  条件生成  

Application of Improved CAGAN in Virtual Try-on
XU Xiaochun,DONG Hongwei,WEI Chengfeng.Application of Improved CAGAN in Virtual Try-on[J].Computer Engineering and Applications,2021,57(6):152-158.
Authors:XU Xiaochun  DONG Hongwei  WEI Chengfeng
Affiliation:School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, China
Abstract:In view of the vague effect of Conditional Analogy GAN(CAGAN) after changing clothes, poor performance when the length of the target clothes is inconsistent with that of the original clothes, too few details are preserved relative to the target clothes, a new virtual try-on method based on improved CAGAN is proposed. The improved CAGAN generates a preliminary result and gets the mask of the target clothes after wearing on the model. Then the target clothes are deformed with mask. The deformed clothes and the results of the first step are combined to obtain the final results. The experimental results show that the method solves the previous problems and achieves very good results.
Keywords:Generative Adversarial Networks(GAN)  virtual try-on  conditional generation  
本文献已被 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号