arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09831cs.CV
收藏

MODIFY:模型驱动的无风格图像的人脸风格化

MODIFY: Model-driven Face Stylization without Style Images

Anhui University(安徽大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

Yuhe Ding, Jian Liang, Jie Cao, Aihua Zheng, Ran He

摘要:

现有的人脸风格化方法在翻译过程中总是获取目标(风格)域的存在,这违反了隐私规则,限制了它们在现实世界系统中的适用性。为了解决这个问题,我们提出了一种新的方法称为MODel驱动的人脸风格化(MODIFY),它依赖于生成模型绕过目标图像的依赖性。简言之,MODIFY首先在目标域中训练生成模型,然后通过所提供的样式模型将源输入翻译到目标域。为了保留多模态样式信息,MODIFY进一步引入了一个额外的重映射网络,将已知的连续分布映射到编码器的嵌入空间中。在源域中的翻译期间,MODIFY在目标风格保持模型中微调编码器模块,以尽可能精确地捕获源输入的内容。我们的方法是非常简单的,并满足多功能的培训模式,面对风格化。在不同数据集上的实验结果验证了MODIFY算法在无监督人脸风格化中的有效性。

英文摘要:

Existing face stylization methods always acquire the presence of the target (style) domain during the translation process, which violates privacy regulations and limits their applicability in real-world systems. To address this issue, we propose a new method called MODel-drIven Face stYlization (MODIFY), which relies on the generative model to bypass the dependence of the target images. Briefly, MODIFY first trains a generative model in the target domain and then translates a source input to the target domain via the provided style model. To preserve the multimodal style information, MODIFY further introduces an additional remapping network, mapping a known continuous distribution into the encoder's embedding space. During translation in the source domain, MODIFY fine-tunes the encoder module within the target style-persevering model to capture the content of the source input as precisely as possible. Our method is extremely simple and satisfies versatile training modes for face stylization. Experimental results on several different datasets validate the effectiveness of MODIFY for unsupervised face stylization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑