StyleGAN

Definition

StyleGAN is a GAN architecture with a newly designed generator. The generator is structured with unsupervised separation of high-level attributes (e.g. pose) and stochastic variation in the generated images.

Architecture

Mapping Network

Instead of feeding random noise directly into the generator, styleGAN uses a mapping network to map the input latent vector into an intermediate latent space $\mathcal{W}$.

Adaptive Instance Normalization (AdaIN)

The AdaIN operation is defined as $\mathrm{AdaIN}(x_i,y)=y_{s,i}\frac{x_i-\mu (x)}{\sigma (x_i)}+y_{b,i}$ where $x_i$ is the $i$-th feature map, $y_{s,i}$ and $y_{b,i}$ are style scale and bias, and $\mu (x_i)$ and $\sigma (x_i)$ are the mean and standard deviation of $x_i$.

The $y_{..}$ are learning parameters, and are generated by affine transformation of the intermediate latent vector $w$. $[y_{s,1},y_{b,1},\dots ,y_{s,n},y_{b,n}]:=Mw+b=A(w)$ where $M$ and $b$ are the trained weight and bias respectively.

It is used to inject the style information at each layer of the generator.

Stochastic variation

The noise image ($B$) is added to each layer of the synthesis network. It provides the stochastic variation in the generated images.

Progressive Growing

The network starts generating low-resolution images and progressively increases the resolution. We can control the rate of style change by controlling the stage AdaIN appended.