StyleGAN: Difference between revisions

 
(2 intermediate revisions by the same user not shown)
Line 12: Line 12:


===Mapping Network===
===Mapping Network===
The goal of the mapping network is to generate plausible "styles" in the form of a latent vector <math>w</math>.<br>
The goal of the mapping network is to generate a latent vector <math>w</math>.<br>
This style <math>w</math> is used by the synthesis network as input the each AdaIn block.<br>
This latent <math>w</math> is used by the synthesis network as input the each AdaIN block.<br>
Before each AdaIN block, a learned affine transformation converts <math>w</math> into a "style" in the form of mean and standard deviation.<br>
The mapping network <math>f</math> consists of 8 fully connected layers with leaky relu activations at each layer.<br>
The mapping network <math>f</math> consists of 8 fully connected layers with leaky relu activations at each layer.<br>
The input and output of this vector is an array of size 512.<br>
The input and output of this vector is an array of size 512.<br>
Line 27: Line 28:
An affine layer (fully connected with no activation, block A in the figure) converts the style to a mean <math>y_{b,i}</math> and standard deviation <math>y_{s,i}</math>.<br>
An affine layer (fully connected with no activation, block A in the figure) converts the style to a mean <math>y_{b,i}</math> and standard deviation <math>y_{s,i}</math>.<br>
Then the feature map is shifted and scaled to have this mean and standard deviation.<br>
Then the feature map is shifted and scaled to have this mean and standard deviation.<br>
* <math>\operatorname{AdaIN(\mathbf{x}_i, \mathbf{y}) = \mathbf{y}_{s,i}\frac{\mathbf{x}_i - \mu(\mathbf{x}_i)}{\sigma(\mathbf{x}_i)} + \mathbf{y}_{b,i}</math>
* <math>\operatorname{AdaIN}(\mathbf{x}_i, \mathbf{y}) = \mathbf{y}_{s,i}\frac{\mathbf{x}_i - \mu(\mathbf{x}_i)}{\sigma(\mathbf{x}_i)} + \mathbf{y}_{b,i}</math>


==Results==
==Results==