Generative Models
-
This repository is for implementation of
Generative Models
using Tensorflow 1.12 -
The structure of the code is based on the Hwalsuk Lee's Generative Model github repository
Contributors
MMC Lab GAN Study Group members
Implemented Paper List (20 Papers)
GAN
- [GAN] Generative Adversarial Networks
- [DCGAN] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- [LSGAN] Least Squares Generative Adversarial Networks
- [WGAN] Wasserstein GAN
- [WGAN_GP] Improved Training of Wasserstein GANs
- [CGAN] Conditional Generative Adversarial Nets
- [InfoGAN] Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- [HoloGAN] Unsupervised Learning of 3D Representations From Natural Images
- [SinGAN] Learning a Generative Model from a Single Natural Image
- [PGGAN] Progressive Growing of GANs for Improved Quality, Stability, and Variation
- [StyleGAN] A Style-Based Generator Architecture for Generative Adversarial Networks
Image-to-Image Translation
- [CycleGAN] Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- [AGGAN] Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
- [StarGAN] Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
- [DMIT] Multi-mapping Image-to-Image Translation via Learning Disentanglement
Interpretable GAN Latent
VAE
- Auto-Encoding Variational Bayes (VAE)
- Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
- Neural Discrete Representation Learning(VQ-VAE)
Application
Our Results
GAN Results
1. GAN
MNIST
2. DCGAN
MNIST | CelebA |
---|---|
3. LSGAN
MNIST | CelebA |
---|---|
4. WGAN
MNIST | CelebA |
---|---|
5. WGAN-GP
MNIST | CelebA |
---|---|
6. Conditional GAN
MNIST
7. InfoGAN
MNIST
8. HoloGAN
CelebA
9. SinGAN
Balloon
Mountain
Starry Night
10. PGGAN
It took about 2 weeks on TITAN RTX and trained 600k images per stage.
1024x1024 images
Cherry picked images
Latent interpolation
Fixed latent
No cherry picked images
11. StyleGAN
CelebA HQ (512x512 images)
Selected images
Style Mixing with Latent Codes
Random Images
AFHQ (512x512 images)
Selected images
Style Mixing with Latent Codes
Random Images
Image-to-Image Translation Results
1. CycleGAN
Monet to Photo | Photo to Monet |
---|---|
Horse to Zebra | Zebra to Horse |
---|---|
2. AGGAN
Horse to Zebra | Zebra to Horse |
---|---|
3. StarGAN
CelebA
4. DMIT
Summer2Winter
Interpretable GAN Latent
1. Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
1) MNIST
VAE Results
1. VAE
Reconstruction
MNIST | CelebA |
---|---|
Latent Space Interpolation (MNIST)
Latent Space Interpolation (CelebA)
2. Beta-VAE
Latent Space Interpolation: Beta = 10 (CelebA)
Latent Space Interpolation: Beta = 200 (CelebA)
3. VQ-VAE
Reconstruction (MNIST)
Input | Reconstruction |
---|---|
Reconstruction (CelebA)
Input | Reconstruction |
---|---|
PixelCNN Trained Latent Decoding
MNIST | CelebA |
---|---|