Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their powerful ability to apply realistic modifications to an image, these methods often lack properties like disentanglement (the capacity to edit attributes independently). In this paper, we propose an auto-encoder which re-organizes the latent space of StyleGAN, so that each attribute which we wish to edit corresponds to an axis of the new latent space, and furthermore that the latent axes are decorrelated, encouraging disentanglement. We work in a compressed version of the latent space, using Principal Component Analysis, meaning that the parameter complexity of our autoencoder is reduced, leading to short training times ($\sim$ 45 mins). Qualitative and quantitative results demonstrate the editing capabilities of our approach, with greater disentanglement than competing methods, while maintaining fidelity to the original image with respect to identity. Our autoencoder architecture simple and straightforward, facilitating implementation.

我们提出了一种自编码器方法，通过重新组织StyleGAN的潜空间，使我们希望编辑的每个属性对应于新潜空间的一个轴，同时确保潜空间轴之间的相关性降到最低，以促进属性解缠，通过实验证明了我们的方法在编辑能力上超越了竞争方法，同时在保持图像身份一致性方面与原始图像具有高度的准确性，我们的自编码器结构简单明了，易于实现。

图像编辑的紧凑且语义潜空间的解缠和可控