Adaptive instance normalization (AdaIN) has become the standard method for style injection: by re-normalizing features through scale-and-shift operations, it has found widespread use in style transfer, image generation, and image-to-image translation. In this work, we present a generalization of AdaIN which relies on the whitening and coloring transformation (WCT) which we dub AdaWCT, that we apply for style injection in large GANs. We show, through experiments on the StarGANv2 architecture, that this generalization, albeit conceptually simple, results in significant improvements in the quality of the generated images.

翻译：适应性实例正常化(AdaIN)已经成为风格注入的标准方法:通过规模和轮班操作重新规范特征,发现在风格传输、图像生成和图像到图像翻译中广泛使用。 在这项工作中,我们展示了AdaIN的概括化,AdaIN依赖于我们称为AdaWCT的白化和彩色转换(WCT),我们申请在大型GANs中采用风格注入。我们通过StarGANv2结构的实验显示,这种概括化尽管在概念上简单,但导致生成图像质量的显著改善。