首页> 外文会议> >Geometry-Aware GAN for Face Attribute Transfer
【24h】

Geometry-Aware GAN for Face Attribute Transfer

机译:用于面部属性传递的几何感知GAN

获取原文

摘要

In this paper, the geometry-aware GAN is proposed to address the issue of facial attribute transfer with unpaired data. To tackle the unpaired training sample problem, the CycleGAN architecture is applied, where the bilateral mappings between the source and target domains are learned. The deformation flow is learned to capture the geometric variation between two domains. We first warp the source face into desired pose and shape according to the flow. Then, the transfer sub-network is designed to refine the results by hallucinating new components on the warped image. The attribute is removed by the reconstruction sub-network, coupled with the warping process. Experiments on benchmark demonstrate the advantages of our method compared to baselines.
机译:在本文中,提出了几何感知的GAN,以解决带有不成对数据的面部属性转移的问题。为了解决不成对的训练样本问题,应用了CycleGAN架构,在该架构中学习了源域和目标域之间的双边映射。学习变形流以捕获两个域之间的几何变化。我们首先根据流将源面扭曲为所需的姿势和形状。然后,将传输子网设计为通过使扭曲图像上的新成分产生幻觉来细化结果。该属性由重构子网以及翘曲过程删除。基准实验证明了我们的方法相比于基线的优势。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号