Methods › Computer Vision › Generative Models
Generative Models
Generative Models aim to model data generatively (rather than discriminatively), that is they aim to approximate the probability distribution of the data. Below you can find a continuously updating list of generative models for computer vision.
Methods
All 63 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| StyleGAN | – | 292 |
| VQ-VAE | – | 197 |
| Denoising Autoencoder | 2008 | 182 |
| Restricted Boltzmann Machine | 1986 | 140 |
| Pix2Pix | – | 132 |
| EBM energy-based model | – | 128 |
| BigGAN | – | 103 |
| cVAE Conditional Variational Auto Encoder | – | 100 |
| DCGAN Deep Convolutional GAN | – | 82 |
| Deep Belief Network | 2009 | 71 |
| GLOW | – | 57 |
| Sparse Autoencoder | – | 57 |
| StyleGAN2 | – | 49 |
| PixelCNN | – | 45 |
| InfoGAN | – | 35 |
| Beta-VAE | – | 30 |
| RAE Regularized Autoencoders | – | 26 |
| Hierarchical VAE Hierarchical Variational Autoencoder | – | 25 |
| NICE Non-linear Independent Component Estimation | – | 22 |
| SAG Self-Attention Guidance | – | 22 |
| RealNVP | – | 19 |
| LSGAN | – | 18 |
| ProGAN Progressively Growing GAN | – | 17 |
| SIG Sliced Iterative Generator | – | 17 |
| BiGAN Bidirectional GAN | – | 15 |
| Deep Boltzmann Machine | – | 14 |
| GEE Generative Emotion Estimator | – | 12 |
| SNGAN Spectrally Normalised GAN | – | 12 |
| BigGAN-deep | – | 11 |
| ALI Adversarially Learned Inference | – | 10 |
| Self-Attention Guidance | – | 7 |
| VQ-VAE-2 | – | 7 |
| LOGAN | – | 6 |
| Contractive Autoencoder | 2011 | 5 |
| LAPGAN | – | 5 |
| NVAE Nouveau VAE | – | 5 |
| OTM Optimal Transport Modeling | – | 5 |
| PAG Perturbed-Attention Guidance | – | 5 |
| SDAE Stacked Denoising Autoencoder | – | 5 |
| BigBiGAN | – | 4 |
| IAN Introspective Adversarial Network | – | 4 |
| PixelRNN Pixel Recurrent Neural Network | – | 4 |
| CS-GAN | – | 3 |
| ControlVAE | – | 3 |
| PFGM Poisson Flow Generative Models | – | 3 |
| TGAN | – | 3 |
| k-Sparse Autoencoder | – | 3 |
| ALAE Adversarial Latent Autoencoder | – | 2 |
| HiSD Hierarchical Style Disentanglement | – | 2 |
| LapStyle Laplacian Pyramid Network | – | 2 |
| StyleALAE | – | 2 |
| Viewmaker Network | – | 2 |
| Attribute2Font | – | 1 |
| CurvVAE Curvature Regularized Variational Auto-Encoder | – | 1 |
| DVD-GAN | – | 1 |
| HDCGAN High-resolution Deep Convolutional Generative Adversarial Networks | – | 1 |
| Informative Sample Mining Network | – | 1 |
| Outlier Generation Outlier Generation in Tabular Data | – | 1 |
| PresGAN Prescribed Generative Adversarial Network | – | 1 |
| Topographic VAE | – | 1 |
| TrIVD-GAN | – | 1 |
| Vision-aided GAN | – | 1 |
| Perturbed-Attention Guidance | – | 0 |