Research map

Image generation: research map

Diffusion, GANs and autoregressive models for images, plus editing, super-resolution and restoration.

8,039 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 7 topics. Within all five venues, its share grew from 7.9% in 2023–24 to 9.0% in 2025–26 (2,084 → 4,093 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Image generation in the interactive map

Topics

• Fast diffusion sampling · 1,866 papers
  Diffusion theory and design space, Distributional control of diffusion, Denoising diffusion probabilistic models
• Autoregressive and latent generation · 1,747 papers
  Generative latent space tooling, High-resolution diffusion synthesis, Latent diffusion with learned tokenizers
• Text-to-image diffusion · 1,310 papers
  Compositional text-to-image guidance, Text-driven synthesis and semantic guidance, Personalized and region-controlled generation
• Image restoration · 1,184 papers
  Dehazing and deraining, Inverse imaging with learned priors, Image harmonization and color transformation
• Editing and style transfer · 988 papers
  Image-to-image translation, Texture and sketch synthesis, Arbitrary neural style transfer
• GANs · 515 papers
  Stabilized GAN training, GAN latent optimization and evaluation, GANs for text generation
• Super-resolution · 429 papers
  Efficient lightweight super-resolution, Perceptual and real-world SR, CNN and transformer SR architectures

Most cited papers in Image generation

• Image-To-Image Translation With Conditional Adversarial Networks (CVPR 2017 · 22,687 citations)
• High-Resolution Image Synthesis With Latent Diffusion Models (CVPR 2022 · 15,775 citations)
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR 2017 · 12,597 citations)
• A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR 2019 · 11,298 citations)
• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR 2016 · 7,310 citations)
• Image Style Transfer Using Convolutional Neural Networks (CVPR 2016 · 6,164 citations)
• Analyzing and Improving the Image Quality of StyleGAN (CVPR 2020 · 6,132 citations)
• Denoising Diffusion Probabilistic Models (NeurIPS 2020 · 5,610 citations)
• Residual Dense Network for Image Super-Resolution (CVPR 2018 · 4,176 citations)
• Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022 · 4,037 citations)
• Spectral Normalization for Generative Adversarial Networks (ICLR 2018 · 3,438 citations)
• Self-Attention Generative Adversarial Networks (ICML 2019 · 2,555 citations)