Methods › Computer Vision › Generative Adversarial Networks › StyleGAN2

StyleGAN2

49 papers tagged archive 2025-07-28

Introduced by Tero Karras et al. in Analyzing and Improving the Image Quality of StyleGAN

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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.

PaperSourceSee Code · NVlabs/stylegan2

Papers archive 2025-07-28

30 shown of 49, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 73 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Generation17
Data Augmentation5
Generative Adversarial Network5
Image Manipulation5
Attribute4
Conditional Image Generation3
Face Generation3
Image Reconstruction3
Image Restoration3
Image-to-Image Translation3
Translation3
Colorization2
Disentanglement2
Face Recognition2
Image Morphing2
Medical Image Generation2
Segmentation2
Super-Resolution2
Vocal Bursts Intensity Prediction2
10-shot image generation1

Usage over time archive 2025-07-28

Papers per year tagged with StyleGAN2: 2019 to 2025, peak 23 23 0 2019: 1 paper 2019 2020: 23 papers 2020 2021: 12 papers 2021 2022: 4 papers 2022 2023: 1 paper 2023 2024: 6 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (49 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Generative Adversarial NetworksGenerative Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections