Transcription of Analyzing and Improving the Image Quality of StyleGAN
{{id}} {{{paragraph}}}
Analyzing and Improving the Image Quality of StyleGANTero KarrasNVIDIAS amuli LaineNVIDIAM iika AittalaNVIDIAJ anne HellstenNVIDIAJ aakko LehtinenNVIDIA and Aalto UniversityTimo AilaNVIDIAA bstractThe style-based GAN architecture ( StyleGAN ) yieldsstate-of-the-art results in data-driven unconditional gener-ative Image modeling. We expose and analyze several ofits characteristic artifacts, and propose changes in bothmodel architecture and training methods to address particular, we redesign the generator normalization, re-visit progressive growing, and regularize the generator toencourage good conditioning in the mapping from latentcodes to images.
additional random noise maps to the synthesis network. It has been demonstrated [21, 33] that this design allows the intermediate latent space W to be much less entangled than the input latent space Z. In this paper, we focus all analy-sis solely on W, as it is the relevant latent space from the synthesis network’s point of view.
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}