Official code (Pytorch) for paper Perception-Enhanced Single Image Super-Resolution via Relativistic Generative Networks
Official implementation for Perception-Enhanced Single Image Super-Resolution via Relativistic Generative Networks ECCV Workshop 2018
Please our project if it is helpful for your research
@InProceedings{Vu_2018_ECCV_Workshops},
author = {Vu, Thang and Luu, Tung M. and Yoo, Chang D.},
title = {Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks},
booktitle = {The European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}
Python3
Pytorch 0.4
tensorboardX
tqdm
imageio
data/origin/
directorycheck_point
directorypython test.py --dataset <DATASET_NAME>
results/
directorydata/origin directory
python train.py --phase pretrain --learning_rate 1e-4
python train.py
check_point/
direcorytensorboard --logdir check_point
YOUR_IP:6006
to your web browser.python test.py --dataset <DATASET> --alpha <ALPHA>
(with alpha being perceptual weight)RED and BLUE indicate best and second best respectively.