Separating Content and Style for Unsupervised Image-to-Image Translation
Separating Content and Style for Unsupervised Image-to-Image Translation
复制标题
DOI：
--
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Yunfei Liu;Haofei Wang;Yang Yue;Feng Lu
中科院分区：
文献类型：
--
作者：
Yunfei Liu;Haofei Wang;Yang Yue;Feng Lu
无监督图像到图像翻译的目的是学习具有非成对样本的两个视觉域之间的映射。现有的工作集中在为多模态目的分离领域不变的内容代码和领域特定的样式代码。然而，对翻译图像的解释和处理却很少受到重视。在本文中，我们提出在一个统一的框架中同时分离内容代码和样式代码。基于潜在特征和高级域不变任务之间的相关性，该框架在翻译图像的多模态翻译、可解释性和可操作性方面表现出优异的性能。实验结果表明，该方法在视觉质量和多样性方面优于现有的无监督图像翻译方法。
Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domain-invariant content code and domain-specific style code individually for multimodal purposes. However, less attention has been paid to interpreting and manipulating the translated image. In this paper, we propose to separate the content code and style code simultaneously in a unified framework. Based on the correlation between the latent features and the high-level domain-invariant tasks, the proposed framework demonstrates superior performance in multimodal translation, interpretability and manipulation of the translated image. Experimental results show that the proposed approach outperforms the existing unsupervised image translation methods in terms of visual quality and diversity.