论文标题
甘斯空间：发现可解释的甘恩控件
GANSpace: Discovering Interpretable GAN Controls
论文作者
论文摘要
本文介绍了一种简单的技术，可以分析生成对抗网络（GAN）并为图像合成创建可解释的控件，例如观点的改变，老化，照明和一天中的时间。我们基于在潜在空间或特征空间中应用的主要组件分析（PCA）确定重要的潜在方向。然后，我们表明，可以通过沿主要方向的层扰动来定义大量可解释的控件。此外，我们表明Biggan可以以类似于样式的方式通过层次输入来控制。我们显示了在各种数据集中受过培训的不同gan的结果，并展示了良好的定性匹配，以编辑通过早期监督方法找到的指示。
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Components Analysis (PCA) applied either in latent space or feature space. Then, we show that a large number of interpretable controls can be defined by layer-wise perturbation along the principal directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches.
