Awesome-GANS-and-Deepfakes
A curated list of GAN & Deepfake papers and repositories.
GANs
Tl;dr GANs containg two competing neural networks which iteratively generate new data with the same statistics as the training set.
Unconditional GANs
βοΈ Vanilla GAN: Generative Adversarial Networks, [paper], [github]- βοΈ DCGAN: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, [paper], [github]
- βοΈ WGAN: Wasserstein GAN, [paper], [github]
- βοΈ WGAN-GP: Improved Training of Wasserstein GANs, [paper], [github]
- βοΈ RGAN: The relativistic discriminator: a key element missing from standard GAN, [paper], [github]
- βοΈ BGAN: Boundary-Seeking Generative Adversarial Networks, [paper], [github]
βοΈ ClusterGAN: Latent Space Clustering in Generative Adversarial Networks, [paper], [github]
Conditional GANs
- βοΈ CGAN: Conditional Generative Adversarial Nets, [paper], [github]
- βοΈ ACGAN: Conditional Image Synthesis With Auxiliary Classifier GANs, [paper], [github]
- βοΈ CCGAN: Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks, [paper], [github]
Image-to-Image Translation
βοΈ CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, [paper], [github]- βοΈ StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation, [paper], [github]
- βοΈ Pix2Pix: Image-to-Image Translation with Conditional Adversarial Nets, [paper], [github]
- βοΈ DualGAN: Unsupervised Dual Learning for Image-to-Image Translation, [paper], [github]
- βοΈ BicycleGAN: Toward Multimodal Image-to-Image Translation, [paper], [github]
Volumetric (3D) Generation
βοΈ 3DGAN: Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, [paper], [github]- βοΈ Inverse Graphics GAN: Inverse Graphics GAN - Learning to Generate 3D Shapes from Unstructured 2D Data, [paper], [github]
Applications using GANs
Anime generator
- Towards the Automatic Anime Characters Creation with Generative Adversarial Networks, [paper]
βοΈ [Project] Keras-GAN-Animeface-Character, [github]
Interactive Image generation
βοΈ Generative Visual Manipulation on the Natural Image Manifold, [paper], [github]βοΈ Neural Photo Editing with Introspective Adversarial Networks, [paper], [github]
3D Object generation
- 3D Shape Induction from 2D Views of Multiple Objects, [paper]
- βοΈ Parametric 3D Exploration with Stacked Adversarial Networks, [github], [youtube]
βοΈ Fully Convolutional Refined Auto-Encoding Generative Adversarial Networks for 3D Multi Object Scenes, [github], [blog]
Super-resolution
- βοΈ Image super-resolution through deep learning, [github]
βοΈ Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, [paper], [github]- High-Quality Face Image Super-Resolution Using Conditional Generative Adversarial Networks, [paper]
- βοΈ Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network, [paper], [github]
βοΈ ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks, [paper], [github]- βοΈ MUNIT: Multimodal Unsupervised Image-to-Image Translation, [paper], [github]
βοΈ SRGAN: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, [paper], [github]
Image Inpainting (hole filling)
βοΈ Context Encoders: Feature Learning by Inpainting, [paper], [github]βοΈ Semantic Image Inpainting with Perceptual and Contextual Losses, [paper], [github]- βοΈ Generative Face Completion, [paper], [github]
Medical Image Segmentation
- βοΈ Vox2Vox: 3D-GAN for Brain Tumor Segmentation, [paper], [github]
- SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation, [paper]
- Generative Adversarial Neural Networks for Pigmented and Non-Pigmented Skin Lesions Detection in Clinical Images, [paper]
Deepfakes
Tl;dr Deepfakes are fake videos or audio recordings that look and sound just like the real thing. Watch this video of Obama speaking... or was that really him?
CNN-based Face-swapping
- βοΈ Fast Face-swap Using Convolutional Neural Networks, [paper], [github]
- βοΈ DeepFaceLab: A simple, flexible and extensible face swapping framework, [paper], [github]
GAN-based Face-swapping
- βοΈ Fewshot Face Translation GAN, [github]
- Faceswap-GAN, [github]
βοΈ AttGAN: Facial Attribute Editing by Only Changing What You Want, [paper], [github]- MulGAN: Facial Attribute Editing by Exemplar, [paper]
- βοΈ MaskGAN: Towards Diverse and Interactive Facial Image Manipulation, [paper], [github]
- βοΈ StarGAN v2: Diverse Image Synthesis for Multiple Domains, [paper], [github]
- βοΈ FSGAN: Subject Agnostic Face Swapping and Reenactment, [paper], [github]
Deepfake Detection
CNN-based methods
- βοΈ MesoNet [paper], [github]
- Detecting Deep-Fake Videos from Phoneme-Viseme Mismatches, [paper]
- Deep Fake Image Detection Based on Pairwise Learning, [paper]
RCN-based methods
- Recurrent Convolutional Strategies for Face Manipulation Detection in Videos, [paper]
Other ML methods
- SVM: Exposing Deep Fakes Using Inconsistent Head Poses, [paper]
Datasets
- Google Deepfake Detection Dataset
- FaceForensics++ Dataset
- Facebook Deepfake Detection Challenge (DFDC) Dataset
- "SwapMe and Faceswap" dataset
- "Fake Faces in the Wild (FFW) dataset
- Tampered Face (TAMFA) Dataset
- Celeb-DF(v2) Celebrity Deepfake Dataset
- DeeperForensics-1.0
- Diverse Fake Face Dataset (DFFD)