Analyzing and Improving the Image Quality of StyleGAN

CVPR 2020 Tero KarrasSamuli LaineMiika AittalaJanne HellstenJaakko LehtinenTimo Aila

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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Generation FFHQ StyleGAN2 FID 2.84 # 1
Image Generation LSUN Car 256 x 256 StyleGAN2 FID 2.32 # 1
Image Generation LSUN Car 512 x 384 StyleGAN2 FID 2.32 # 1
Image Generation LSUN Cat 256 x 256 StyleGAN2 FID 6.93 # 1
Image Generation LSUN Churches 256 x 256 StyleGAN2 FID 3.86 # 1
Image Generation LSUN Churches 256 x 256 StyleGAN FID 4.21 # 2
Image Generation LSUN Horse 256 x 256 StyleGAN2 FID 3.43 # 1

Methods used in the Paper