论文标题
Stylegan潜在空间中基于张量的情感编辑
Tensor-based Emotion Editing in the StyleGAN Latent Space
论文作者
论文摘要
在本文中，我们使用基于高阶单数值分解（HOSVD）的张量模型来发现生成对抗网络中的语义方向。这是通过首先使用E4E编码器将结构化面部表达数据库嵌入潜在空间中来实现的。具体来说，我们在潜在空间中发现了与六种原型情绪相对应的潜在空间的指示：愤怒，厌恶，恐惧，幸福，悲伤和惊喜，以及偏航旋转的方向。这些潜在的空间方向用于改变真实面部图像的表达或偏航旋转。我们将发现的方向与其他两种方法发现的类似方向进行了比较。结果表明，所得编辑的视觉质量与最先进的相当。还可以得出结论，基于张量的模型非常适合情感和偏航编辑，即，新颖的面部图像的情绪或偏航旋转可以牢固地改变，而不会对图像中的身份或其他属性产生重大影响。
In this paper, we use a tensor model based on the Higher-Order Singular Value Decomposition (HOSVD) to discover semantic directions in Generative Adversarial Networks. This is achieved by first embedding a structured facial expression database into the latent space using the e4e encoder. Specifically, we discover directions in latent space corresponding to the six prototypical emotions: anger, disgust, fear, happiness, sadness, and surprise, as well as a direction for yaw rotation. These latent space directions are employed to change the expression or yaw rotation of real face images. We compare our found directions to similar directions found by two other methods. The results show that the visual quality of the resultant edits are on par with State-of-the-Art. It can also be concluded that the tensor-based model is well suited for emotion and yaw editing, i.e., that the emotion or yaw rotation of a novel face image can be robustly changed without a significant effect on identity or other attributes in the images.
