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.

METHOD YEAR PAPERS
AutoEncoder
2006 1523
GAN
2014 1177
VAE
2013 475
CycleGAN
2017 150
Denoising Autoencoder
2008 92
Restricted Boltzmann Machine
1986 90
WGAN
2017 51
Deep Belief Network
2009 51
DCGAN
2015 43
SAGAN
2018 41
StyleGAN
2018 39
BigGAN
2018 33
cVAE
2015 29
Pix2Pix
2016 27
VQ-VAE
2017 24
PixelCNN
2016 23
GLOW
2018 19
InfoGAN
2016 18
SRGAN
2016 17
Sparse Autoencoder
2000 15
StyleGAN2
2019 13
Deep Boltzmann Machine
2000 13
LSGAN
2016 12
Beta-VAE
2017 12
BiGAN
2016 9
WGAN GP
2017 9
RealNVP
2016 9
SNGAN
2018 8
LAPGAN
2015 4
SDAE
2000 4
ProGAN
2017 4
DE-GAN
2000 4
BigGAN-deep
2018 3
PixelRNN
2016 3
ALI
2016 3
BigBiGAN
2019 3
Contractive Autoencoder
2011 3
Relativistic GAN
2018 3
NICE
2014 2
LOGAN
2019 2
TGAN
2016 2
CS-GAN
2019 2
IAN
2016 1
DVD-GAN
2019 1
VQ-VAE-2
2019 1
TrIVD-GAN
2020 1
NVAE
2020 1
k-Sparse Autoencoder
2013 1
SIG
2020 1
PresGAN
2019 1
HDCGAN
2017 1