论文标题
$ s^2 $ - 流：面部图像的联合语义和样式编辑
$S^2$-Flow: Joint Semantic and Style Editing of Facial Images
论文作者
论文摘要
生成对抗网络（GAN）产生的高质量图像激发了对其图像编辑应用的调查。但是，gan通常在执行特定编辑的控制中受到限制。主要挑战之一是gan的纠缠潜在空间，它不适合执行独立和详细的编辑。最近的编辑方法允许进行受控的样式编辑或受控的语义编辑。此外，使用语义掩码编辑图像的方法难以保留身份并且无法执行受控的样式编辑。我们提出了一种将gan $ \ text {'} $ s潜在空间分解为语义和样式空间的方法，从而在同一框架中独立地独立于面部图像进行控制的语义和样式编辑。为了实现这一目标，我们设计了一个基于编码器的网络体系结构（$ s^2 $ -Flow），其中包含了两个提出的电感偏见。我们通过执行各种语义和样式的编辑来表明$ s^2 $流量的适用性。
The high-quality images yielded by generative adversarial networks (GANs) have motivated investigations into their application for image editing. However, GANs are often limited in the control they provide for performing specific edits. One of the principal challenges is the entangled latent space of GANs, which is not directly suitable for performing independent and detailed edits. Recent editing methods allow for either controlled style edits or controlled semantic edits. In addition, methods that use semantic masks to edit images have difficulty preserving the identity and are unable to perform controlled style edits. We propose a method to disentangle a GAN$\text{'}$s latent space into semantic and style spaces, enabling controlled semantic and style edits for face images independently within the same framework. To achieve this, we design an encoder-decoder based network architecture ($S^2$-Flow), which incorporates two proposed inductive biases. We show the suitability of $S^2$-Flow quantitatively and qualitatively by performing various semantic and style edits.
