AdaWCT: Adaptive Whitening and Coloring Style Injection
This work addresses style injection for image generation tasks, but it is incremental as it builds upon existing AdaIN methods.
The paper tackled the problem of style injection in generative adversarial networks (GANs) by generalizing adaptive instance normalization (AdaIN) to an adaptive whitening and coloring transformation (AdaWCT), resulting in significant improvements in generated image quality as demonstrated on StarGANv2.
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.