Tiny Face Super Resolution
Prerequisites
- python 3.6
- pytorch 0.4.1
- ubuntu 16.04
Network:
- DBPN
- RSGAN
- Perceptual Loss
Results:
Reference:
- Deep Back-Projection Networks For Super-Resolution. Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita.
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, Wenzhe Shi.
- The relativistic discriminator: a key element missing from standard GAN. Alexia Jolicoeur-Martineau.
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang.
Acknowledge:
- Reference Code DBPN-Pytorch