The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs, making them unfit for in-the-wild low-quality (LQ) images, which are common inputs for manipulation. In this work, we bridge this gap by proposing a novel GAN structure that allows for generating images with controllable quality. The network can synthesize various image degradation and restore the sharp image via a quality control code. Our proposed QC-StyleGAN can directly edit LQ images without altering their quality by applying GAN inversion and manipulation techniques. It also provides for free an image restoration solution that can handle various degradations, including noise, blur, compression artifacts, and their mixtures. Finally, we demonstrate numerous other applications such as image degradation synthesis, transfer, and interpolation.

翻译：引入高质量的图像生成模型,特别是StyleGAN家族,为合成和操作图像提供了一个强有力的工具,然而,现有模型建立在高质量(HQ)数据的基础上,作为预期产出,使其不适于使用内部的低质量(LQ)图像,这些图像是常见的操作投入。在这项工作中,我们提出一个新的GAN结构,以便能够以可控质量生成图像,从而弥补这一差距。网络可以通过质量控制代码合成各种图像降解并恢复锐利图像。我们提议的 QC-StyleGAN 可以直接编辑LQ图像,而不会通过应用 GAN 的转换和操作技术改变其质量。它还提供免费的图像恢复解决方案,可以处理各种降解,包括噪音、模糊、压缩文物及其混合物。最后,我们展示了图像降解合成、传输和内插等许多其他应用。