This repository is as a research project in the field of super resolution. It uses RDN as the generator and spectral norm is used in discriminator.
The residual dense network has many advantages for reconstructing SR images, and we use GANs to enhance RDN. The core idea is from the following two papers:
- Residual Dense Network for Image Super-Resolution
- cGANs with projection discriminator
These results is just trained about 200,000 iterations (full: 600,000) with batch size of 16.
| Raw | Bicubic(x4) | RDN_GAN(x4) |
|---|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
[1] Zhang Y, Tian Y, Kong Y, et al. Residual dense network for image super-resolution[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018.
[2] Miyato T, Koyama M. cGANs with projection discriminator[J]. arXiv preprint arXiv:1802.05637, 2018.