Generative Adversarial Networks (GANs) are currently an indispensable tool for visual editing, being a standard component of image-to-image translation and image restoration pipelines. Furthermore, GANs are especially useful for controllable generation since their latent spaces contain a wide range of interpretable directions, well suited for semantic editing operations. By gradually changing latent codes along these directions, one can produce impressive visual effects, unattainable without GANs. In this paper, we significantly expand the range of visual effects achievable with the state-of-the-art models, like StyleGAN2. In contrast to existing works, which mostly operate by latent codes, we discover interpretable directions in the space of the generator parameters. By several simple methods, we explore this space and demonstrate that it also contains a plethora of interpretable directions, which are an excellent source of non-trivial semantic manipulations. The discovered manipulations cannot be achieved by transforming the latent codes and can be used to edit both synthetic and real images. We release our code and models and hope they will serve as a handy tool for further efforts on GAN-based image editing.
翻译:图像生成自动网络(GANs)目前是视觉编辑不可或缺的工具,是图像到图像翻译和图像恢复管道的标准组成部分。此外,GANs对于可控生成特别有用,因为其潜在空间包含广泛的可解释方向,非常适合语义编辑操作。通过在这些方向上逐步改变潜伏代码,人们可以产生令人印象深刻的视觉效果,没有GANs则无法实现。在本文中,我们大幅扩展了与最新模型(如StyleGAN2)可实现的视觉效果的范围。与大多数由潜伏代码操作的现有工程相比,我们发现在生成参数空间内的可解释方向。我们通过几种简单的方法探索这一空间,并表明它也包含大量的可解释方向,这是非三角语义的操纵的极好来源。所发现的操纵无法通过改变潜在代码实现,并且能够用于编辑合成和真实图像。我们发布了我们的代码和模型,希望它们能成为GAN基图像编辑的进一步努力的手动工具。