总结 | 这里有关于GAN学习资源的一切（论文、应用、课程、书籍……）

来源：新智元

本文约2600字，建议阅读10分钟。

本文为你整理了关于GAN的一切知识。

[ 导读 ]想了解关于GAN的一切？已经有人帮你整理好了！从论文资源、到应用实例，再到书籍、教程和入门指引，不管是新人还是老手，都能有所收获。

本文是一篇关于GAN开源资源的一篇分类汇总贴。全文共分为论文、应用、课程、书籍和入门指南五个部分，比较硬核的论文和应用实例部分放在前面，课程、入门指导等内容则放在文末。

无论是对于初学者还是老手，相信本文的内容都会对你有所帮助。对于论文和应用部分，一般先给出论文链接，然后给出GitHub软件资源。

第一部分：论文及GAN的分类

本节所列为与GAN相关的一些核心论文。首先是提出并创建GAN的基本概念的基本论文。然后逐次分类介绍GAN的一些常见变体的论文。

GAN (VanillaGAN)

• Generative Adversarial Nets

http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf

https://github.com/goodfeli/adversarial

• Energy-Based Generative Adversarial Network  

https://arxiv.org/pdf/1609.03126v2.pdf

https://github.com/buriburisuri/ebgan

• Which Training Methods for GANs do Actually Converge

https://arxiv.org/pdf/1801.04406.pdf

https://github.com/LMescheder/GAN_stability

条件GAN  (CGAN)

• Conditional generative adversarial nets

https://arxiv.org/abs/1411.1784

https://github.com/zhangqianhui/Conditional-GAN

• Photo-realistic single image super-resolution using a GAN

https://arxiv.org/pdf/1609.04802.pdf

https://github.com/tensorlayer/srgan

• Image-to-Image Translation with Conditional Adversarial Networks

https://arxiv.org/abs/1611.07004

https://github.com/phillipi/pix2pix

• Generative Visual Manipulation on the Natural Image Manifold

https://arxiv.org/abs/1609.03552

https://github.com/junyanz/iGAN

拉普拉斯金字塔对抗网络 (LAPGAN)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

http://papers.nips.cc/paper/5773-deep-generative-image-models-using-a-laplacian-pyramid-of-adversarial-networks.pdf

https://github.com/witnessai/LAPGAN

深度卷积GAN (DCGAN)

• Deep Convolutional Generative Adversarial Networks

http://papers.nips.cc/paper/5773-deep-generative-image-models-using-a-laplacian-pyramid-of-adversarial-networks.pdf

https://github.com/witnessai/LAPGAN

• Generative Adversarial Text to Image Synthesis

https://arxiv.org/pdf/1605.05396.pdf

https://github.com/reedscot/icml2016

对抗性自动编码器 (AAE)

• Adversarial Autoencoders

https://arxiv.org/abs/1511.05644

https://github.com/Naresh1318/Adversarial_Autoencoder

生成递归对抗网络 (GRAN)

• Generating images with recurrent adversarial networks

https://arxiv.org/abs/1602.05110

https://github.com/jiwoongim/GRAN

信息最大化GAN  (InfoGAN)

• Infogan: Information maximizing GANs

http://papers.nips.cc/paper/6399-infogan-interpretable-representation

https://github.com/openai/InfoGAN

第二部分：应用实例

关于GAN的理论与训练

• Energy-based generative adversarial network

https://arxiv.org/pdf/1609.03126v2.pdf

https://github.com/buriburisuri/ebgan

• Which Training Methods for GANs do actually Converge

https://arxiv.org/pdf/1801.04406.pdf

https://github.com/LMescheder/GAN_stability

• Improved Techniques for Training GANs

https://arxiv.org/abs/1609.04468

https://github.com/openai/improved-gan

• Towards Principled Methods for Training Generative Adversarial Networks

https://arxiv.org/abs/1701.04862

• Least Squares Generative Adversarial Networks

https://arxiv.org/abs/1611.04076

https://github.com/pfnet-research/chainer-LSGAN

• Wasserstein GAN

https://arxiv.org/abs/1701.07875

https://github.com/martinarjovsky/WassersteinGAN

• Improved Training of Wasserstein GANs

https://arxiv.org/abs/1704.00028

https://github.com/igul222/improved_wgan_training

• Generalization and Equilibrium in Generative Adversarial Nets

https://arxiv.org/abs/1703.00573

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

http://papers.nips.cc/paper/7240-gans-trained-by-a-two-t

https://github.com/bioinf-jku/TTUR

图像解析

• Generative Adversarial Text to Image Synthesis

https://arxiv.org/abs/1605.05396

https://github.com/reedscot/icml201

• Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

https://arxiv.org/abs/1612.00005v1

https://github.com/Evolving-AI-Lab/ppgn

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

https://arxiv.org/abs/1511.06434

https://github.com/jacobgil/keras-dcgan

• Progressive Growing of GANs for Improved Quality, Stability, and Variation

http://research.nvidia.com/publication/2017-10_Progressive-Growing-of

https://github.com/tkarras/progressive_growing_of_gans

• StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

https://arxiv.org/pdf/1612.03242v1.pdf

https://github.com/hanzhanggit/StackGAN

• Self-Attention Generative Adversarial Networks

https://arxiv.org/abs/1805.08318

https://github.com/heykeetae/Self-Attention-GAN

• Large Scale GAN Training for High Fidelity Natural Image Synthesis

https://arxiv.org/abs/1809.11096

图-图转换

• Image-to-image translation using conditional adversarial nets

https://arxiv.org/pdf/1611.07004v1.pdf

https://github.com/phillipi/pix2pix

• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

https://arxiv.org/abs/1703.05192

https://github.com/carpedm20/DiscoGAN-pytorch

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

https://junyanz.github.io/CycleGAN/

https://github.com/junyanz/CycleGAN

• CoGAN: Coupled Generative Adversarial Networks

https://arxiv.org/abs/1606.07536

https://github.com/andrewliao11/CoGAN-tensorflow

• Unsupervised Image-to-Image Translation Networks

https://arxiv.org/abs/1703.00848

• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

https://arxiv.org/abs/1711.11585

• UNIT: UNsupervised Image-to-image Translation Networks

https://arxiv.org/abs/1703.00848

https://github.com/mingyuliutw/UNIT

• Multimodal Unsupervised Image-to-Image Translation

https://arxiv.org/abs/1804.04732

https://github.com/nvlabs/MUNIt

超解析度

• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

https://arxiv.org/abs/1609.04802

https://github.com/leehomyc/Photo-Realistic-Super-Resoluton

• High-Quality Face Image Super-Resolution Using Conditional Generative Adversarial Networks

https://arxiv.org/pdf/1707.00737.pdf

• Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network

https://arxiv.org/pdf/1811.00344.pdf

https://github.com/subeeshvasu/2018_subeesh_epsr_eccvw

文本-图像转换

• TAC-GAN – Text Conditioned Auxiliary Classifier Generative Adversarial Network

https://arxiv.org/pdf/1703.06412.pdf

https://github.com/dashayushman/TAC-GAN

• Generative Adversarial Text to Image Synthesis

https://arxiv.org/pdf/1605.05396.pdf

https://github.com/paarthneekhara/text-to-imag

• Learning What and Where to Draw

http://www.scottreed.info/files/nips2016.pdf

https://github.com/reedscot/nips2016

图片编辑

• Invertible Conditional GANs for image editing

https://arxiv.org/pdf/1611.06355.pdf

https://github.com/Guim3/IcGAN

• Image De-raining Using a Conditional Generative Adversarial Network

https://arxiv.org/abs/1701.05957

https://github.com/hezhangsprinter/ID-CGAN

其他应用

• Generating multi-label discrete patient records using generative adversarial networks

https://arxiv.org/abs/1703.06490

https://github.com/mp2893/medgan

• Adversarial Generation of Natural Language

https://arxiv.org/abs/1705.10929

• Language Generation with Recurrent Generative Adversarial Networks without Pre-training

https://arxiv.org/abs/1706.01399

https://github.com/amirbar/rnn.wgan

• Adversarial ranking for language generation

http://papers.nips.cc/paper/6908-adversarial-ranking-for-language-generation

https://github.com/desire2020/RankGAN

• Adversarial Training Methods for Semi-Supervised Text Classification

https://arxiv.org/abs/1605.07725

https://github.com/aonotas/adversarial_text

第三部分：课程

• Deep Learning: GANs and Variational Autoencoders by Udemy:

https://www.udemy.com/deep-learning-gans-and-variational-autoencoders/

Differentiable Inference and Generative Models by the University of

• Toronto:

http://www.cs.toronto.edu/~duvenaud/courses/csc2541/

• Learning Generative Adversarial Networks by Udemy:

https://www.udemy.com/learning-generative-adversarial-networks/

第四部分：参考书籍

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

https://www.manning.com/books/gans-in-action

第五部分：一些入门指南

• GANs from Scratch 1: A deep introduction

https://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f

• Keep Calm and train a GAN. Pitfalls and Tips on training Generative Adversarial Networks:

https://medium.com/@utk.is.here/keep-calm-and-train-a-gan-pitfalls-and-tips-on-training-generative-adversarial-networks-edd529764aa9

• CVPR 2018 Tutorial on GANs: 

https://sites.google.com/view/cvpr2018tutorialongans/

• Introductory guide to Generative Adversarial Networks (GANs) and their promise!: 

https://www.analyticsvidhya.com/blog/2017/06/introductory-generative-adversarial-networks-gans/

• Generative Adversarial Networks for beginners: 

https://www.oreilly.com/learning/generative-adversarial-networks-for-beginners

• Understanding and building Generative Adversarial Networks(GANs): 

https://becominghuman.ai/understanding-and-building-generative-adversarial-networks-gans-8de7c1dc0e25

参考链接：

https://machinelearningmindset.com/generative-adversarial-networks-roadmap/

编辑：王菁

校对：林亦霖