The purpose of this article is to introduce a roadmap for developers and researcher to find useful resources about Generative Adversarial Networks.



There are different motivations for this open source project. The organization of the resources is such that the user can easily find the things he/she is looking for. We divided the resources to a large number of categories that in the beginning one may have a headache!!! However, if someone knows what is being located, it is very easy to find the most related resources. Even if someone doesn’t know what to look for, in the beginning, the list of resources have been provided.



This chapter is associated with the papers published associated with generative adversarial Networks.

Types and Models (Core)


Image by: Rouzbeh Asghari Shirvani

Core: Generative Adversarial Networks (VanillaGAN)
Generative Adversarial NetsPaperCodeRate star2 star2 star2 star2 star2
Which Training Methods for GANs do Actually ConvergePaperCodeRate star2 star2
Conditional Generative Adversarial Networks (CGAN)
Conditional generative adversarial netsPaperCodeRate star2 star2 star2 star2 star2
Photo-realistic single image super-resolution using a GANPaperCodeRate star2 star2 star2 star2
Image-to-Image Translation with Conditional Adversarial NetworksPaperCodeRate star2 star2 star2 star2
Generative Visual Manipulation on the Natural Image ManifoldPaperCodeRate star2 star2
Laplacian Pyramid of Adversarial Networks (LAPGAN)
Deep Generative Image Models using a Laplacian Pyramid of Adversarial NetworksPaperCodeRate star2 star2 star2 star2 star2
Deep Convolutional Generative Adversarial Networks (DCGAN)
Deep Convolutional Generative Adversarial NetworksPaperCodeRate star2 star2 star2 star2 star2
Generative Adversarial Text to Image SynthesisPaperCodeRate star2 star2 star2
Adversarial Autoencoders (AAE)
Adversarial AutoencodersPaperCodeRate star2 star2 star2 star2 star2
Generative Recurrent Adversarial Networks (GRAN)
Generating images with recurrent adversarial networksPaperCodeRate star2 star2 star2 star2
Information Maximizing Generative Adversarial Networks (InfoGan)
Infogan: Information maximizing GANsPaperCodeRate star2 star2 star2 star2 star2


GANs Theory and Training

Energy-based generative adversarial networkPaperCode
Which Training Methods for GANs do actually ConvergePaperCode
Improved Techniques for Training GANsPaperCode
Towards Principled Methods for Training Generative Adversarial NetworksPaper 
Least Squares Generative Adversarial NetworksPaperCode
Wasserstein GANPaperCode
Improved Training of Wasserstein GANsPaperCode
Generalization and Equilibrium in Generative Adversarial NetsPaper 
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash EquilibriumPaperCode
Spectral Normalization for Generative Adversarial Networks

Image Synthesis

Generative Adversarial Text to Image SynthesisPaperCode
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent SpacePaperCode
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial NetworksPaperCode
Progressive Growing of GANs for Improved Quality, Stability, and VariationPaperCode
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial NetworksPaperCode
Self-Attention Generative Adversarial NetworksPaperCode
Large Scale GAN Training for High Fidelity Natural Image SynthesisPaper 

Image-to-image translation

Image-to-image translation using conditional adversarial netsPaperCode
Learning to Discover Cross-Domain Relations with Generative Adversarial NetworksPaperCode
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksPaperCode
CoGAN: Coupled Generative Adversarial NetworksPaperCode
Unsupervised Image-to-Image Translation NetworksPaper 
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANsPaper 
UNIT: UNsupervised Image-to-image Translation NetworksPaperCode
Multimodal Unsupervised Image-to-Image TranslationPaperCode


Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial NetworkPaperCode
High-Quality Face Image Super-Resolution Using Conditional Generative Adversarial NetworksPaper 
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution NetworkPaperCode

Text to Image

TAC-GAN – Text Conditioned Auxiliary Classifier Generative Adversarial NetworkPaperCode
Generative Adversarial Text to Image SynthesisPaperCode
Learning What and Where to DrawPaperCode

Image Editing

Invertible Conditional GANs for image editingPaperCode
Image De-raining Using a Conditional Generative Adversarial NetworkPaperCode


Generating multi-label discrete patient records using generative adversarial networksPaperCode
Adversarial Generation of Natural LanguagePaper 
Language Generation with Recurrent Generative Adversarial Networks without Pre-trainingPaperCode
Adversarial ranking for language generationPaperCode
Adversarial Training Methods for Semi-Supervised Text ClassificationPaperCode



  • Deep Learning: GANs and Variational Autoencoders by Udemy: [Link]
  • Differentiable Inference and Generative Models by the University of Toronto: [Link]
  • Learning Generative Adversarial Networks by Udemy: [Link]



  • GANs in Action – Deep learning with Generative Adversarial Networks by manning Publications: [Link]



  • GANs from Scratch 1: A deep introduction. With code in PyTorch and TensorFlow: [Link]
  • Keep Calm and train a GAN. Pitfalls and Tips on training Generative Adversarial Networks: [Link]
  • CVPR 2018 Tutorial on GANs: [Link]
  • Introductory guide to Generative Adversarial Networks (GANs) and their promise!: [Link]
  • Generative Adversarial Networks for beginners: [Link]
  • Understanding and building Generative Adversarial Networks(GANs): [Link]


Here, we gathered and summarized useful resources about Generative Adversarial Networks. Your are welcome to contribute and help this collection to grow by referring to the project GitHub repository.


Amirsina Torfi

Currently, as a CS Ph.D. student, I'm a research assistant at Virginia Tech. My research is mainly about Machine Learning & Deep Learning and their applications in Computer Vision and NLP. I'm interested in developing software packages and open-source projects.

Leave a Reply

Notify of