StyleGAN2 is a generative adversarial network that builds on StyleGAN with several improvements. First, adaptive instance normalization is redesigned and replaced with a normalization technique called weight demodulation. Secondly, an improved training scheme upon progressively growing is introduced, which achieves the same goal - training starts by focusing on low-resolution images and then progressively shifts focus to higher and higher resolutions - without changing the network topology during training. Additionally, new types of regularization like lazy regularization and path length regularization are proposed.
Source: Analyzing and Improving the Image Quality of StyleGANPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 17 | 17.17% |
Image Manipulation | 5 | 5.05% |
Face Generation | 3 | 3.03% |
Face Recognition | 3 | 3.03% |
Image Reconstruction | 3 | 3.03% |
Image-to-Image Translation | 3 | 3.03% |
Image Restoration | 3 | 3.03% |
Translation | 3 | 3.03% |
Conditional Image Generation | 3 | 3.03% |
Component | Type |
|
---|---|---|
![]() |
Convolutions | |
![]() |
Activation Functions | |
![]() |
Regularization | |
![]() |
Regularization | |
![]() |
Normalization |