Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Analyzing and Improving the Image Quality of StyleGAN

About

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 the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes 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 attribute a generated image to 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 redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, Timo Aila• 2019

Related benchmarks

TaskDatasetResultRank
Unconditional Image GenerationCIFAR-10 (test)
FID5.6
216
Unconditional Image GenerationCIFAR-10 unconditional
FID2.92
159
Image GenerationCIFAR10 32x32 (test)
FID8.32
154
Unconditional GenerationCIFAR-10 (test)
FID8.32
102
Unconditional Image GenerationLSUN Bedrooms unconditional
FID2.35
96
Image GenerationLSUN church
FID3.86
95
Unconditional Image GenerationCelebA unconditional 64 x 64
FID3.39
95
Image GenerationCIFAR-10
FID6.96
95
Image GenerationLSUN Bedroom 256x256 (test)
FID3.98
73
Conditional Image GenerationCIFAR-10
FID2.42
71
Showing 10 of 209 rows
...

Other info

Code

Follow for update