StyleGAN 中的人脸身份感知解耦
Face Identity-Aware Disentanglement in StyleGAN
AI总结：
本文提出 StyleGAN 插件 PluGeN4Faces，利用电影帧中同一人物的多姿态图像和对比损失实现人脸属性与身份解耦，使属性编辑对身份等其余特征的干扰显著低于现有方法。
摘要：
条件 GAN 经常被用于操控人脸图像的属性，例如表情、发型、姿态或年龄。尽管最先进的模型能够成功修改所请求的属性，但它们同时也会修改图像的其他重要特征，例如人物身份。本文聚焦于解决这一问题，提出了 PluGeN4Faces，一个 StyleGAN 的插件，能够显式地将人脸属性与人物身份解耦。我们的核心思路是利用从电影帧中提取的图像进行训练，在这些图像中，同一个人以不同的姿态和不同的属性出现。通过应用一种对比损失，我们鼓励模型将同一个人的图像聚集在潜在空间的相似区域。我们的实验表明，与现有的最先进模型相比，PluGeN4Faces 对人脸属性的修改对图像其余特征的侵入性显著更低。
英文摘要：
Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age. Even though the state-of-the-art models successfully modify the requested attributes, they simultaneously modify other important characteristics of the image, such as a person's identity. In this paper, we focus on solving this problem by introducing PluGeN4Faces, a plugin to StyleGAN, which explicitly disentangles face attributes from a person's identity. Our key idea is to perform training on images retrieved from movie frames, where a given person appears in various poses and with different attributes. By applying a type of contrastive loss, we encourage the model to group images of the same person in similar regions of latent space. Our experiments demonstrate that the modifications of face attributes performed by PluGeN4Faces are significantly less invasive on the remaining characteristics of the image than in the existing state-of-the-art models.
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。
