Only awesome is awesome. This is a curation, not a collection.
This list is about what GANs are used for. General GAN papers whose contribution is the model
itself (DCGAN, BEGAN, WGAN, …) are not included as entries — only genuine landmarks make the
short list at the top. Pure theory / loss-function papers are out of scope; diffusion-only work is
out of scope (GAN+diffusion hybrids are fine).
🏷 Legend: 📄 paper · 💻 code · 🌐 project/demo · 🎬 video · 📝 blog
🤝 Contributions welcome — see CONTRIBUTING.md.
| Paper | Venue | Year | Links |
|---|
| Generative Adversarial Networks | NeurIPS | 2014 | 📄 💻 |
| Unsupervised Representation Learning with Deep Convolutional GANs (DCGAN) | ICLR | 2016 | 📄 💻 |
| Improved Techniques for Training GANs | NeurIPS | 2016 | 📄 💻 |
| BEGAN: Boundary Equilibrium Generative Adversarial Networks | — | 2017 | 📄 💻 |
| Training Generative Adversarial Networks with Limited Data (StyleGAN2-ADA) | NeurIPS | 2020 | 📄 💻 |
| The GAN is dead; long live the GAN! A Modern GAN Baseline (R3GAN) | NeurIPS | 2024 | 📄 💻 |
Click to expand the table of contents — or just press command/ctrl + F to search for a keyword.
| Title | Venue | Year | Links |
|---|
| Learning Chinese Character Style with Conditional GAN (zi2zi) | — | 2017 | 💻 📝 |
| Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning (AGIS-Net) | SIGGRAPH Asia | 2019 | 📄 💻 |
| Attribute2Font: Creating Fonts You Want From Attributes | SIGGRAPH | 2020 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Towards the Automatic Anime Characters Creation with GANs | — | 2017 | 📄 |
| AnimeGANv2: Photo to Anime Style Transfer | — | 2021 | 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| JoJoGAN: One Shot Face Stylization | ECCV | 2022 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Generative Visual Manipulation on the Natural Image Manifold (iGAN) | ECCV | 2016 | 📄 💻 |
| Neural Photo Editing with Introspective Adversarial Networks | ICLR | 2017 | 📄 💻 |
| Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold (DragGAN) | SIGGRAPH | 2023 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery | ICCV | 2021 | 📄 💻 |
| Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation (pSp) | CVPR | 2021 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| TAC-GAN: Text Conditioned Auxiliary Classifier GAN | — | 2017 | 📄 💻 |
| StackGAN: Text to Photo-realistic Image Synthesis with Stacked GANs | ICCV | 2017 | 📄 💻 |
| Generative Adversarial Text to Image Synthesis | ICML | 2016 | 📄 💻 💻 |
| Learning What and Where to Draw | NeurIPS | 2016 | 📄 💻 |
| AttnGAN: Fine-Grained Text to Image Generation with Attentional GANs | CVPR | 2018 | 📄 💻 |
| GigaGAN: Scaling up GANs for Text-to-Image Synthesis | CVPR | 2023 | 📄 |
| StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis | ICML | 2023 | 📄 💻 |
↑ back to Contents
GANs strike back in 2024–2026: adversarial objectives distill slow diffusion samplers into one/few-step image and video generators — where GANs are most alive in 2025–2026.
| Title | Venue | Year | Links |
|---|
| UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs | CVPR | 2024 | 📄 |
| Improved Distribution Matching Distillation for Fast Image Synthesis (DMD2) | NeurIPS | 2024 | 📄 💻 |
| SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation | arXiv | 2025 | 📄 💻 |
| Diffusion Adversarial Post-Training for One-Step Video Generation (Seaweed-APT) | ICML | 2025 | 📄 🌐 |
| Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation (Seaweed-APT2) | NeurIPS | 2025 | 📄 🌐 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Parametric 3D Exploration with Stacked Adversarial Networks (pix2vox) | — | 2016 | 💻 🎬 |
| Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (3D-GAN) | NeurIPS | 2016 | 📄 💻 🎬 |
| 3D Shape Induction from 2D Views of Multiple Objects | — | 2016 | 📄 |
| Fully Convolutional Refined Auto-Encoding GANs for 3D Multi Object Scenes | — | 2017 | 💻 📝 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Efficient Geometry-aware 3D Generative Adversarial Networks (EG3D) | CVPR | 2022 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Invertible Conditional GANs for Image Editing (IcGAN) | — | 2016 | 📄 💻 |
| Image De-raining Using a Conditional GAN (ID-CGAN) | — | 2017 | 📄 💻 |
| DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks | CVPR | 2018 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE) | CVPR | 2017 | 📄 💻 |
| CAN: Creative Adversarial Networks Generating "Art" | — | 2017 | 📄 |
| Face Aging with Conditional Generative Adversarial Networks | — | 2017 | 📄 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Joint Discriminative and Generative Learning for Person Re-identification (DG-Net) | CVPR | 2019 | 📄 💻 🎬 |
| Pose Guided Person Image Generation | NeurIPS | 2017 | 📄 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| First Order Motion Model for Image Animation | NeurIPS | 2019 | 📄 💻 |
| A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild (Wav2Lip) | ACM MM | 2020 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization | CVPR | 2021 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) | CVPR | 2017 | 📄 💻 🎬 |
| Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (CycleGAN) | ICCV | 2017 | 📄 💻 🎬 |
| Learning to Discover Cross-Domain Relations with GANs (DiscoGAN) | ICML | 2017 | 📄 💻 |
| StarGAN: Unified Multi-Domain Image-to-Image Translation | CVPR | 2018 | 📄 💻 |
| StarGAN v2: Diverse Image Synthesis for Multiple Domains | CVPR | 2020 | 📄 💻 |
| Multimodal Unsupervised Image-to-Image Translation (MUNIT) | ECCV | 2018 | 📄 💻 |
| Unsupervised Creation of Parameterized Avatars | — | 2017 | 📄 |
| Unsupervised Cross-Domain Image Generation (DTN) | ICLR | 2017 | 📄 |
| Precomputed Real-Time Texture Synthesis with Markovian GANs (MGANs) | ECCV | 2016 | 📄 💻 |
| Pixel-Level Domain Transfer (PixelDTGAN) | ECCV | 2016 | 📄 💻 |
| TextureGAN: Controlling Deep Image Synthesis with Texture Patches | CVPR | 2018 | 📄 🌐 |
| Vincent AI Sketch Demo (NVIDIA, GTC Europe) | — | 2017 | 📝 🎬 |
| Deep Photo Style Transfer | CVPR | 2017 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Context Encoders: Feature Learning by Inpainting | CVPR | 2016 | 📄 💻 |
| Semantic Image Inpainting with Perceptual and Contextual Losses | CVPR | 2017 | 📄 💻 |
| Semi-Supervised Learning with Context-Conditional GANs | — | 2016 | 📄 |
| Free-Form Image Inpainting with Gated Convolution (DeepFill v2) | ICCV | 2019 | 📄 💻 |
| Resolution-robust Large Mask Inpainting with Fourier Convolutions (LaMa) | WACV | 2022 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| GP-GAN: Towards Realistic High-Resolution Image Blending | ACM MM | 2019 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Image Super-Resolution Through Deep Learning (srez) | — | 2016 | 💻 |
| Photo-Realistic Single Image Super-Resolution Using a GAN (SRGAN) | CVPR | 2017 | 📄 💻 |
| High-Quality Face Image Super-Resolution Using Conditional GANs | — | 2017 | 📄 |
| Analyzing Perception-Distortion Tradeoff (EPSR) | ECCVW | 2018 | 📄 💻 |
| ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks | ECCVW | 2018 | 📄 💻 |
| Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data | ICCVW | 2021 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Generating Large Images from Latent Vectors | — | 2016 | 💻 📝 |
| Progressive Growing of GANs for Improved Quality, Stability, and Variation (PGGAN) | ICLR | 2018 | 📄 💻 |
| Large Scale GAN Training for High Fidelity Natural Image Synthesis (BigGAN) | ICLR | 2019 | 📄 |
| SinGAN: Learning a Generative Model from a Single Natural Image | ICCV | 2019 | 📄 💻 |
| Analyzing and Improving the Image Quality of StyleGAN (StyleGAN2) | CVPR | 2020 | 📄 💻 |
| Alias-Free Generative Adversarial Networks (StyleGAN3) | NeurIPS | 2021 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| SafetyNet: Detecting and Rejecting Adversarial Examples Robustly | ICCV | 2017 | 📄 |
| Adversarial Examples for Generative Models | — | 2017 | 📄 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| SalGAN: Visual Saliency Prediction with Generative Adversarial Networks | — | 2017 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Perceptual Generative Adversarial Networks for Small Object Detection | CVPR | 2017 | 📄 |
| Adversarial Generation of Training Examples for Vehicle License Plate Recognition | — | 2017 | 📄 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Deep Multi-Scale Video Prediction Beyond Mean Square Error | ICLR | 2016 | 📄 💻 |
| Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation (TecoGAN) | SIGGRAPH | 2020 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Adversarial Audio Synthesis (WaveGAN) | ICLR | 2019 | 📄 💻 |
| HiFi-GAN: GANs for Efficient and High Fidelity Speech Synthesis | NeurIPS | 2020 | 📄 💻 |
| BigVGAN: A Universal Neural Vocoder with Large-Scale Training (v2 2024) | ICLR | 2023 | 📄 💻 |
| Vocos: Closing the Gap between Time-domain and Fourier-based Neural Vocoders | ICLR | 2024 | 📄 💻 |
| BemaGANv2: Discriminator Combination Strategies for GAN-based Vocoders in Long-Term Audio | arXiv | 2025 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient | AAAI | 2017 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Unsupervised Anomaly Detection with GANs to Guide Marker Discovery (AnoGAN) | IPMI | 2017 | 📄 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Learning from Simulated and Unsupervised Images through Adversarial Training (SimGAN) | CVPR | 2017 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| (Physics) Location-Aware Generative Adversarial Networks for Physics Synthesis | — | 2017 | 📄 💻 |
| (General) Spectral Normalization for Generative Adversarial Networks | ICLR | 2018 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction (MoFA) | ICCV | 2017 | 📄 💻 🎬 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup | SIGGRAPH | 2016 | 🌐 🎬 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies | SIGGRAPH | 2016 | 🎬 |
| PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing | SIGGRAPH | 2009 | 📄 💻 🎬 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation | — | 2017 | 📄 💻 |
↑ back to Contents
| Title | Venue | Year | Links |
|---|
| 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction | ECCV | 2016 | 📄 💻 |
↑ back to Contents
↑ back to Contents
Genuinely awesome, widely-used GitHub repos built on GANs — usable code and tools, not just papers. Star counts update automatically.
↑ back to Contents
↑ back to Contents
↑ back to Contents
Minchul Shin, @nashory
Any recommendations to add to the list are welcome — see CONTRIBUTING.md and feel free to make pull requests! :)
