Jie Huang+, Man Zhou+, Yajing Liu, Mingde Yao, Feng Zhao*, Zhiwei Xiong

*Corresponding Author

+Equal Contributions

University of Science and Technology of China (USTC)

This repository is the official implementation of the paper, "Exposure-Consistency Representation Learning for Exposure Correction", where more implementation details are presented.

Overall, most parameters can be set in options/train/train_Enhance.yml

Create a .txt file to put the path of the dataset using

python create_txt.py

python train.py --opt options/train/train_Enhance.yml

set is_training in "options/train/train_Enhance.yml" as False set the val:filelist as the validation set.

then

python train.py --opt options/train/train_Enhance.yml

MSEC dataset (please refer to https://github.com/mahmoudnafifi/Exposure_Correction)

SICE dataset (I have uploaded it to https://share.weiyun.com/C2aJ1Cti)

coming soon

If you have any problem with the released code, please do not hesitate to contact me by email (hj0117@mail.ustc.edu.cn).