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 1388
GAN
2014 1195
VAE
2013 426
CycleGAN
2017 136
Denoising Autoencoder
2008 86
Restricted Boltzmann Machine
1986 85
Deep Belief Network
2009 51
WGAN
2017 49
DCGAN
2015 42
StyleGAN
2018 34
SAGAN
2018 33
BigGAN
2018 26
Pix2Pix
2016 25
PixelCNN
2016 22
VQ-VAE
2017 21
InfoGAN
2016 17
SRGAN
2016 16
GLOW
2018 15
Sparse Autoencoder
2000 15
Deep Boltzmann Machine
2000 13
LSGAN
2016 12
Beta-VAE
2017 12
BiGAN
2016 9
RealNVP
2016 9
StyleGAN2
2019 8
WGAN GP
2017 8
SNGAN
2018 6
LAPGAN
2015 4
PixelRNN
2016 3
ALI
2016 3
BigBiGAN
2019 3
Contractive Autoencoder
2011 3
ProGAN
2017 3
Relativistic GAN
2018 3
BigGAN-deep
2018 2
CS-GAN
2019 2
NICE
2014 1
IAN
2016 1
HDCGAN
2017 1
DVD-GAN
2019 1
VQ-VAE-2
2019 1
TGAN
2016 1
LOGAN
2019 1
NVAE
2020 1
TrIVD-GAN
2020 1
k-Sparse Autoencoder
2013 1
SIG
2020 1
PresGAN
2019 1