By Zhi-Song, Li-Wen Wang, Marie-Paule Cani and Wan-Chi Siu

This repo only provides simple testing codes, pretrained models and the network strategy demo.

We propose a joint image denoising and Super-Resolution model by using generative Variational AutoEncoder (dSRVAE)

• First working on using Variational AutoEncoder for image denoising.

• Then the Super-Resolution Sub-Network (SRSN) is attached as a small overhead to the DAE which forms the proposed dSRVAE to output super-resolved images.

Python > 3.0
OpenCV library
Pytorch > 1.2 
NVIDIA GPU + CUDA

The complete architecture is shown as follows,

1. Download pre-trained models from

https://drive.google.com/open?id=1SUZGE04vw5_yDYiw6PJ4sbHAOIEV6TJ7

and copy them to the folder "models"

2. Copy your image to folder "Test" and run

$ python test.py

The SR images will be in folder "Result"

https://drive.google.com/open?id=10ZutE-0idGFW0KUyfZ5-2aVSiA-1qUCV

https://drive.google.com/open?id=1_R4kRO_029g-HNAzPobo4-xwp86bMZLW

https://drive.google.com/open?id=1nKEJ4N2V-0NFicfJxm8AJqsjXoGMYjMp

https://competitions.codalab.org/competitions/22220#learn_the_details

1. Train the Denoising VAE by running

$ python main.py

2. Train the super-resolution SRSN overhead by running

$ python main_GAN.py

Results on 4x image SR on Track 1 dataset