Research map / Image generation
GANs: research map
780 papers on GANs in Image generation, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 2 clusters and 8 approaches. The busiest year so far is 2020.
What it is
Generative adversarial networks train two networks against each other: a generator that makes images and a discriminator that tries to tell them from real ones. GANs produced the first photorealistic faces; research covers stable training, controlling and editing their latent space, and theory.
Terms you will see on this page:
- Generator and discriminator
- the network that synthesises samples and the one that judges real versus fake.
- Mode collapse
- the generator producing only a few kinds of output.
- Latent space editing
- changing attributes of a generated image by moving its latent code.
Start reading with the most cited papers here:
- A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR 2019 · 11,298 citations)
- Analyzing and Improving the Image Quality of StyleGAN (CVPR 2020 · 6,132 citations)
Within Image generation, its share shrank from 2.8% in 2023–24 to 0.6% in 2025–26 (58 → 25 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).
Explore GANs in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
What changed recently
Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):
- GAN-based image manipulation rising: 17% → 28% of the topic (10 → 7 papers)
- Stabilized GAN training falling: 41% → 36% of the topic (24 → 9 papers)
- Large-scale GAN latent analysis falling: 17% → 16% of the topic (10 → 4 papers)
Papers from 2025–2026 that are already cited most:
- Style Quantization for Data-Efficient GAN Training (CVPR 2025 · 2 citations)
Approaches and key papers
GAN synthesis and manipulation · 394 papers
Keywords: synthesis, latent, face
Approaches in this cluster:
- Large-scale GAN latent analysis (183 papers)
Train high-fidelity GANs and analyze their latent semantics. - GAN-based image manipulation (157 papers)
Apply GANs to editing, translation, and domain-specific image synthesis. - Conditional GANs (40 papers)
Improve conditional image synthesis with diversity and contrastive objectives. - GAN vocoders and audio synthesis (14 papers)
Synthesize speech and audio waveforms with adversarial networks.
Most cited and most cited since 2024:
- A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR 2019 · 11,298 citations)
- Analyzing and Improving the Image Quality of StyleGAN (CVPR 2020 · 6,132 citations)
- Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning (CVPR 2024 · 20 citations)
- Procedural Level Generation with Diffusion Models from a Single Example (AAAI 2024 · 9 citations)
GAN training and theory · 386 papers
Keywords: gans, mode, samples
Approaches in this cluster:
- Stabilized GAN training (200 papers)
Improve GAN stability, convergence, and limited-data training with new objectives and discriminators. - GAN latent optimization and evaluation (78 papers)
Improve generators via latent optimization, pretrained GANs, optimal transport, and divergence-based evaluation. - GANs for text generation (22 papers)
Train discrete text generators adversarially with feature matching and imitation objectives. - Generative adversarial network theory (86 papers)
Analyzes and stabilizes GAN training through kernels, Langevin dynamics and structure preservation.
Most cited and most cited since 2024:
- Spectral Normalization for Generative Adversarial Networks (ICLR 2018 · 3,438 citations)
- Self-Attention Generative Adversarial Networks (ICML 2019 · 2,555 citations)
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks (AAAI 2024 · 14 citations)
- Generative Model Perception Rectification Algorithm for Trade-Off between Diversity and Quality (AAAI 2024 · 12 citations)
Related topics in Image generation
- Autoregressive and latent generation (2,100)
- Super-resolution (771)
- Editing and style transfer (1,430)
- Fast diffusion sampling (2,155)
- Image restoration (2,009)
- Text-to-image diffusion (1,916)
