Awesome paper list with code about generative adversarial nets
By zhangqianhui

deep-learning gan adversarial-networks image-translation


Awesome papers about Generative Adversarial Networks. Majority of papers are related to Image Translation.


Please help contribute this list by contacting [Me][[email protected]] or add pull request

Table of Contents

First paper

:heavy_check_mark: [Generative Adversarial Nets]
- [Paper][Code](NIPS 2014)

Image Translation

- [Paper][Code]

:heavy_check_mark: [Image-to-image translation using conditional adversarial nets]
- [Paper][Code][Code]

:heavy_check_mark: [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks]
- [Paper][Code]

:heavy_check_mark: [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks]
- [Paper][Code]

:heavy_check_mark: [CoGAN: Coupled Generative Adversarial Networks]
- [Paper][Code](NIPS 2016)

:heavy_check_mark: [Unsupervised Image-to-Image Translation with Generative Adversarial Networks]
- [Paper](NIPS 2017)

:heavy_check_mark: [DualGAN: Unsupervised Dual Learning for Image-to-Image Translation]
- [Paper](NIPS 2017)[Code]

:heavy_check_mark: [Unsupervised Image-to-Image Translation Networks]
- [Paper]

:heavy_check_mark: [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs]
- [Paper][code]

:heavy_check_mark: [XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings]
- [Paper]

:heavy_check_mark: [UNIT: UNsupervised Image-to-image Translation Networks]
- [Paper][Code](NIPS 2017)

:heavy_check_mark: [Toward Multimodal Image-to-Image Translation]
- [Paper][Code](NIPS 2017)

:heavy_check_mark: [Multimodal Unsupervised Image-to-Image Translation]
- [Paper][Code]

:heavy_check_mark: [Video-to-Video Synthesis]
- [Paper][Code]

:heavy_check_mark: [Everybody Dance Now]
- [Paper][Code]

:heavy_check_mark: [Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation]
- [Paper](CVPR 2019)

:heavy_check_mark: [Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation]
- [Paper][Code](CVPR 2019 oral)

:heavy_check_mark: [Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation]
- [Paper][Code](CVPR 2020)

:heavy_check_mark: [StarGAN v2: Diverse Image Synthesis for Multiple Domains]
- [Paper][Code](CVPR 2020)

:heavy_check_mark: [Structural-analogy from a Single Image Pair]
- [Paper][Code]

:heavy_check_mark: [High-Resolution Daytime Translation Without Domain Labels]
- [Paper][Code]

:heavy_check_mark: [Rethinking the Truly Unsupervised Image-to-Image Translation]
- [Paper][Code]

:heavy_check_mark: [Diverse Image Generation via Self-Conditioned GANs]
- [Paper][Code](CVPR2020)

:heavy_check_mark: [Contrastive Learning for Unpaired Image-to-Image Translation]
- [Paper][Code](ECCV2020)

Facial Attribute Manipulation

:heavy_check_mark: [Autoencoding beyond pixels using a learned similarity metric]
- [Paper][code][Tensorflow code](ICML 2016)

:heavy_check_mark: [Coupled Generative Adversarial Networks]
- [Paper][Caffe Code][Tensorflow Code](NIPS 2016)

:heavy_check_mark: [Invertible Conditional GANs for image editing]
- [Paper][Code](Arxiv 2016)

:heavy_check_mark: [Learning Residual Images for Face Attribute Manipulation]
- [Paper][code](CVPR 2017)

:heavy_check_mark: [Neural Photo Editing with Introspective Adversarial Networks]
- [Paper][Code](ICLR 2017)

:heavy_check_mark: [Neural Face Editing with Intrinsic Image Disentangling]
- [Paper](CVPR 2017)

:heavy_check_mark: [GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data ]
- [Paper][code](BMVC 2017)

:heavy_check_mark: [Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis]
- [Paper](ICCV 2017)

:heavy_check_mark: [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation]
- [Paper][code](CVPR 2018)

:heavy_check_mark: [Arbitrary Facial Attribute Editing: Only Change What You Want]
- [Paper][code](TIP 2019)

:heavy_check_mark: [ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes]
- [Paper][code](ECCV 2018)

:heavy_check_mark: [Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation]
- [Paper][code](ACM MM2018 oral)

:heavy_check_mark: [GANimation: Anatomically-aware Facial Animation from a Single Image]
- [Paper][code](ECCV 2018 oral)

:heavy_check_mark: [Geometry Guided Adversarial Facial Expression Synthesis]
- [Paper](ACM MM2018)

:heavy_check_mark: [STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing]
- [Paper][code](CVPR 2019)

:heavy_check_mark: [3d guided fine-grained face manipulation] [Paper](CVPR 2019)

:heavy_check_mark: [SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color]
- [Paper][code](ICCV 2019)

:heavy_check_mark: [A Survey of Deep Facial Attribute Analysis]
- [Paper](IJCV 2019)

:heavy_check_mark: [PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing]
- [Paper][code](Arxiv 2020)

:heavy_check_mark: [SSCGAN: Facial Attribute Editing via StyleSkip Connections]
- [Paper](ECCV 2020)

:heavy_check_mark: [CAFE-GAN: Arbitrary Face Attribute Editingwith Complementary Attention Feature]
- [Paper](ECCV 2020)

Generative Models

:heavy_check_mark: [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks]
- [Paper][Code](Gan with convolutional networks)(ICLR 2015)

:heavy_check_mark: [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks]
- [Paper][Code](NIPS 2015)

:heavy_check_mark: [Generative Adversarial Text to Image Synthesis]
- [Paper][Code][code]

:heavy_check_mark: [Improved Techniques for Training GANs]
- [Paper][Code](Goodfellow's paper)

:heavy_check_mark: [Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space]
- [Paper][Code]

:heavy_check_mark: [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks]
- [Paper][Code]

:heavy_check_mark: [Improved Training of Wasserstein GANs]
- [Paper][Code]

:heavy_check_mark: [Boundary Equibilibrium Generative Adversarial Networks]
- [Paper][Code]

:heavy_check_mark: [Progressive Growing of GANs for Improved Quality, Stability, and Variation]
- [Paper][Code][Tensorflow Code]

:heavy_check_mark: [ Self-Attention Generative Adversarial Networks ]
- [Paper][Code](NIPS 2018)

:heavy_check_mark: [Large Scale GAN Training for High Fidelity Natural Image Synthesis]
- [Paper](ICLR 2019)

:heavy_check_mark: [A Style-Based Generator Architecture for Generative Adversarial Networks]
- [Paper][Code]

:heavy_check_mark: [Analyzing and Improving the Image Quality of StyleGAN]
- [Paper][Code]

:heavy_check_mark: [SinGAN: Learning a Generative Model from a Single Natural Image]
- [Paper][Code](ICCV2019 best paper)

:heavy_check_mark: [Real or Not Real, that is the Question]
- [Paper][Code](ICLR2020 Spot)

:heavy_check_mark: [Training End-to-end Single Image Generators without GANs]
- [Paper]

:heavy_check_mark: [Adversarial Latent Autoencoders]
- [Paper][code]

Gaze Correction and Redirection

:heavy_check_mark: [DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation]
- [Paper][code](ECCV 2016)

:heavy_check_mark: [Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks]
- [Paper][Code](ICCV 2019)

:heavy_check_mark: [GazeCorrection:Self-Guided Eye Manipulation in the wild using Self-Supervised Generative Adversarial Networks]
- [Paper][code]

:heavy_check_mark: [MGGR: MultiModal-Guided Gaze Redirection with Coarse-to-Fine Learning]
- [Paper]

:heavy_check_mark: [Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild]
- [Paper][Code](ACM MM2020)


:heavy_check_mark: [AutoGAN: Neural Architecture Search for Generative Adversarial Networks]
- [Paper][Code](ICCV 2019)

Image Animation

:heavy_check_mark: [Animating arbitrary objects via deep motion transfer]
- [Paper][code](CVPR 2019)

:heavy_check_mark: [First Order Motion Model for Image Animation]
- [Paper][code](NIPS 2019)

GAN Theory

:heavy_check_mark: [Energy-based generative adversarial network]
- [Paper][Code](Lecun paper)

:heavy_check_mark: [Improved Techniques for Training GANs]
- [Paper][Code](Goodfellow's paper)

:heavy_check_mark: [Mode Regularized Generative Adversarial Networks]
- [Paper](Yoshua Bengio , ICLR 2017)

:heavy_check_mark: [Improving Generative Adversarial Networks with Denoising Feature Matching]
- [Paper][Code](Yoshua Bengio , ICLR 2017)

:heavy_check_mark: [Sampling Generative Networks]
- [Paper][Code]

:heavy_check_mark: [How to train Gans]
- [Docu]

:heavy_check_mark: [Towards Principled Methods for Training Generative Adversarial Networks]
- [Paper](ICLR 2017)

:heavy_check_mark: [Unrolled Generative Adversarial Networks]
- [Paper][Code](ICLR 2017)

:heavy_check_mark: [Least Squares Generative Adversarial Networks]
- [Paper][Code](ICCV 2017)

:heavy_check_mark: [Wasserstein GAN]
- [Paper][Code]

:heavy_check_mark: [Improved Training of Wasserstein GANs]
- [Paper][Code](The improve of wgan)

:heavy_check_mark: [Towards Principled Methods for Training Generative Adversarial Networks]
- [Paper]

:heavy_check_mark: [Generalization and Equilibrium in Generative Adversarial Nets]
- [Paper](ICML 2017)

:heavy_check_mark: [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium]
- [Paper][code]

:heavy_check_mark: [Spectral Normalization for Generative Adversarial Networks]
- [Paper][code](ICLR 2018)

:heavy_check_mark: [Which Training Methods for GANs do actually Converge]
- [Paper][code](ICML 2018)

:heavy_check_mark: [Self-Supervised Generative Adversarial Networks]
- [Paper][code](CVPR 2019)

Image Inpainting

:heavy_check_mark: [Semantic Image Inpainting with Perceptual and Contextual Losses]
- [Paper][Code](CVPR 2017)

:heavy_check_mark: [Context Encoders: Feature Learning by Inpainting]
- [Paper][Code]

:heavy_check_mark: [Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks]
- [Paper]

:heavy_check_mark: [Generative face completion]
- [Paper][code](CVPR2017)

:heavy_check_mark: [Globally and Locally Consistent Image Completion]
- [MainPAGE][code](SIGGRAPH 2017)

:heavy_check_mark: [High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis]
- [Paper][code](CVPR 2017)

:heavy_check_mark: [Eye In-Painting with Exemplar Generative Adversarial Networks]
- [Paper][Introduction][Tensorflow code](CVPR2018)

:heavy_check_mark: [Generative Image Inpainting with Contextual Attention]
- [Paper][Project][Demo][YouTube][Code](CVPR2018)

:heavy_check_mark: [Free-Form Image Inpainting with Gated Convolution]
- [Paper][Project][YouTube]

:heavy_check_mark: [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning]
- [Paper][Code]

Scene Generation

:heavy_check_mark: [a layer-based sequential framework for scene generation with gans]
- [Paper][Code](AAAI 2019)

Semi-Supervised Learning

:heavy_check_mark: [Adversarial Training Methods for Semi-Supervised Text Classification]
- [Paper][Note]( Ian Goodfellow Paper)

:heavy_check_mark: [Improved Techniques for Training GANs]
- [Paper][Code](Goodfellow's paper)

:heavy_check_mark: [Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks]
- [Paper](ICLR)

:heavy_check_mark: [Semi-Supervised QA with Generative Domain-Adaptive Nets]
- [Paper](ACL 2017)

:heavy_check_mark: [Good Semi-supervised Learning that Requires a Bad GAN]
- [Paper][Code](NIPS 2017)


:heavy_check_mark: [AdaGAN: Boosting Generative Models]
- [Paper][[Code]](Google Brain)

Image blending

:heavy_check_mark: [GP-GAN: Towards Realistic High-Resolution Image Blending]
- [Paper][Code]


:heavy_check_mark: [Joint Discriminative and Generative Learning for Person Re-identification]
- [Paper][Code][YouTube] [Bilibili] (CVPR2019 Oral)

:heavy_check_mark: [Pose-Normalized Image Generation for Person Re-identification]
- [Paper][Code](ECCV 2018)


:heavy_check_mark: [Image super-resolution through deep learning]
- [Code](Just for face dataset)

:heavy_check_mark: [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network]
- [Paper][Code](Using Deep residual network)

:heavy_check_mark: [EnhanceGAN]
- [Docs][[Code]]

:heavy_check_mark: [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks]
- [Paper][Code](ECCV 2018 workshop)


:heavy_check_mark: [Robust LSTM-Autoencoders for Face De-Occlusion in the Wild]
- [Paper]

Semantic Segmentation

:heavy_check_mark: [Adversarial Deep Structural Networks for Mammographic Mass Segmentation]
- [Paper][Code]

:heavy_check_mark: [Semantic Segmentation using Adversarial Networks]
- [Paper](soumith's paper)

Object Detection

:heavy_check_mark: [Perceptual generative adversarial networks for small object detection]
- [Paper](CVPR 2017)

:heavy_check_mark: [A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection]
- [Paper][code](CVPR2017)

Landmark Detection

:heavy_check_mark: [Style aggregated network for facial landmark detection]
- [Paper](CVPR 2018)

Conditional Adversarial

:heavy_check_mark: [Conditional Generative Adversarial Nets]
- [Paper][Code]

:heavy_check_mark: [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets]
- [Paper][Code][Code]

:heavy_check_mark: [Conditional Image Synthesis With Auxiliary Classifier GANs]
- [Paper][Code](GoogleBrain ICLR 2017)

:heavy_check_mark: [Pixel-Level Domain Transfer]
- [Paper][Code]

:heavy_check_mark: [Invertible Conditional GANs for image editing]
- [Paper][Code]

:heavy_check_mark: [Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space]
- [Paper][Code]

:heavy_check_mark: [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks]
- [Paper][Code]

Video Prediction and Generation

:heavy_check_mark: [Deep multi-scale video prediction beyond mean square error]
- [Paper][Code](Yann LeCun's paper)

:heavy_check_mark: [Generating Videos with Scene Dynamics]
- [Paper][Web][Code]

:heavy_check_mark: [MoCoGAN: Decomposing Motion and Content for Video Generation]
- [Paper]

Shadow Detection and Removal

:heavy_check_mark: [ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal]
- [Paper][Code](ICCV 2019)


:heavy_check_mark: [BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial Network]
- [Paper](ACMMM 2018)

Reinforcement learning

:heavy_check_mark: [Connecting Generative Adversarial Networks and Actor-Critic Methods]
- [Paper](NIPS 2016 workshop)


:heavy_check_mark: [C-RNN-GAN: Continuous recurrent neural networks with adversarial training]
- [Paper][Code]

:heavy_check_mark: [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient]
- [Paper][Code](AAAI 2017)


:heavy_check_mark: [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery]
- [Paper]


:heavy_check_mark: [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling]
- [Paper][Web][code](2016 NIPS)

:heavy_check_mark: [Transformation-Grounded Image Generation Network for Novel 3D View Synthesis]
- [Web](CVPR 2017)


:heavy_check_mark: [MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation using 1D and 2D Conditions]
- [Paper][HOMEPAGE]

Discrete distributions

:heavy_check_mark: [Maximum-Likelihood Augmented Discrete Generative Adversarial Networks]
- [Paper]

:heavy_check_mark: [Boundary-Seeking Generative Adversarial Networks]
- [Paper]

:heavy_check_mark: [GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution]
- [Paper]

Improving Classification And Recong

:heavy_check_mark: [Generative OpenMax for Multi-Class Open Set Classification]
- [Paper](BMVC 2017)

:heavy_check_mark: [Controllable Invariance through Adversarial Feature Learning]
- [Paper][code](NIPS 2017)

:heavy_check_mark: [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro]
- [Paper][Code] (ICCV2017)

:heavy_check_mark: [Learning from Simulated and Unsupervised Images through Adversarial Training]
- [Paper][code](Apple paper, CVPR 2017 Best Paper)

:heavy_check_mark: [GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification]
- [Paper] (Neurocomputing Journal (2018), Elsevier)


:heavy_check_mark: [cleverhans]
- [Code](A library for benchmarking vulnerability to adversarial examples)

:heavy_check_mark: [reset-cppn-gan-tensorflow]
- [Code](Using Residual Generative Adversarial Networks and Variational Auto-encoder techniques to produce high resolution images)

:heavy_check_mark: [HyperGAN]
- [Code](Open source GAN focused on scale and usability)


| Author | Address |
| inFERENCe | Adversarial network |
| inFERENCe | InfoGan |
| distill | Deconvolution and Image Generation |
| yingzhenli | Gan theory |
| OpenAI | Generative model |


:heavy_check_mark: [1] http://www.iangoodfellow.com/slides/2016-12-04-NIPS.pdf (NIPS Goodfellow Slides)[Chinese Trans][details]

:heavy_check_mark: [2] [PDF](NIPS Lecun Slides)

:heavy_check_mark: [3] [ICCV 2017 Tutorial About GANS]

:heavy_check_mark: [3] [A Mathematical Introduction to Generative Adversarial Nets (GAN)]