Here is a resource library of low-light image enhancement papers based on the cell vibration theory. It runs very fast. Specifically: Using MATLAB platform, 4500W pixel color image only needs 1.8s running time. The paper has been accepted by IEEE Transactions on Multimedia (IEEE TMM) on May 12, 2022. The encryption code and demo are now available for download.
The encrypted code available for testing can be downloaded. You can use this https URL（访问码：n3n7) or pCloud URL to download the algorithm demo.
Updated on 6, June, 2022: a function script was added.
Updated on 16, July, 2022: scripts related to fast guided filter algorithm were added.
20 images displayed in the paper can be downloaded at this https URL（访问码：mgj4）or pCloud URL (size = 13.51MB).
250 pairs of images in HDR dataset can be downloaded at this https URL or pCloud URL (size = 352MB).
The zip file contains two folders, the 'lowlight' folder and the 'Refimg' folder.
'lowlight' folder contains 250 images under low light.
'Refimg' folder contains 250 images under normal light.
Note:
1.Please do not change the serial number of the images. They correspond to each other. e.g. 'HDRR(1).PNG' is the reference image under normal illumination of 'HDRL(1).PNG'.
2.Please click this address to see more about the original HDR dataset.
If you think the data set and code we collate are helpful for your research, please cite:
@article{CDEF,
title={Low-light Image Enhancement Using the Cell Vibration Model},
author={Xiaozhou Lei, Zixiang Fei, Wenju Zhou, Huiyu Zhou and Minrui Fei},
journal={IEEE Transactions on Multimedia},
year={2022}
month={05}
day={19}
doi={10.1109/TMM.2022.3175634}
}