AI Paper Atlas

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:

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).

2016: 8162017: 48172018: 104182019: 124192020: 137202021: 123212022: 98222023: 53232024: 47242025: 24252026: 1426

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):

Papers from 2025–2026 that are already cited most:

Approaches and key papers

GAN synthesis and manipulation · 394 papers
Keywords: synthesis, latent, face

Approaches in this cluster:

Most cited and most cited since 2024:

GAN training and theory · 386 papers
Keywords: gans, mode, samples

Approaches in this cluster:

Most cited and most cited since 2024:

Related topics in Image generation

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy