Methods > Computer Vision

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 1838
GAN
2014 1166
VAE
2013 561
CycleGAN
2017 180
Denoising Autoencoder
2008 101
Restricted Boltzmann Machine
1986 97
StyleGAN
2018 70
WGAN
2017 58
Deep Belief Network
2009 53
SAGAN
2018 51
DCGAN
2015 50
BigGAN
2018 42
Pix2Pix
2016 40
StyleGAN2
2019 38
VQ-VAE
2017 37
cVAE
2015 34
PixelCNN
2016 24
GLOW
2018 21
InfoGAN
2016 21
SRGAN
2016 21
Sparse Autoencoder
2000 15
LSGAN
2016 14
Beta-VAE
2017 14
Deep Boltzmann Machine
2000 14
RealNVP
2016 11
BiGAN
2016 10
Hierarchical VAE
2016 9
WGAN GP
2017 8
SNGAN
2018 8
ProGAN
2017 7
BigGAN-deep
2018 5
NICE
2014 4
LAPGAN
2015 4
Relativistic GAN
2018 4
SDAE
2000 4
Contractive Autoencoder
2011 3
PixelRNN
2016 3
LOGAN
2019 3
BigBiGAN
2019 3
ALI
2016 3
DE-GAN
2000 3
Style Transfer Module
2017 3
TGAN
2016 2
IAN
2016 2
VQ-VAE-2
2019 2
CS-GAN
2019 2
NVAE
2020 2
ACGPN
2020 2
DVD-GAN
2019 1
TrIVD-GAN
2020 1
k-Sparse Autoencoder
2013 1
PresGAN
2019 1
HDCGAN
2017 1
SIG
2020 1
U-Net GAN
2020 1
ALIS
2021 1