Abstract
The style-based GAN architecture (StyleGAN) yields
state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its
characteristic artifacts, and propose changes in both model
architecture and training methods to address them. In particular, we redesign generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent vectors
to images. In addition to improving image quality, this path
length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it
possible to reliably detect if an image is generated by a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity
problem, motivating us to train larger models for additional
quality improvements. Overall, our improved model rede-
fines the state of the art in unconditional image modeling,
both in terms of existing distribution quality metrics as well
as perceived image quality.
1