Tensorflow implementation of Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones (ECCV 2018 Workshop PIRM)
[Paper_download][Paper_CVF][Paper_Springer]
The schematics of the proposed network for image super-resolution
First, download the DIV2K dataset and unzip it in train_SR/
folder.
Run the following command to train the SR model
python train_SR.py
First, download the SR_Test_Datasets and put them in test/SR_test_data
folder.
Run the following command to super-resolve low-resolution images
python evaluate_super_resolution.py
DPED image enhanced by our method
The structure of the proposed generator and discriminator for image enhancement
train/vgg_pretrained/
foldertrain/dped/
folder.python train_teacher.py
python train_student.py
Run the following command to enhance low-quality images
python evaluate_enhancement.py
If you find PPCN useful in your research, please consider citing:
@inproceedings{Hui-PPCN-2018,
title={Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones},
author={Hui, Zheng and Wang, Xiumei and Deng, Lirui and Gao, Xinbo},
booktitle={ECCV Workshop},
pages = {197--213},
year={2018}
}
[1]https://github.com/aiff22/ai-challenge
[2]https://github.com/aiff22/DPED
[3]https://github.com/roimehrez/contextualLoss