Home

Awesome

RetinexDIP

The pytorch implementation of RetinexDIP: A Unified Deep Framework for Low-light Image Enhancement.

Z. Zhao, B. Xiong, L. Wang, Q. Ou, L. Yu and F. Kuang, "RetinexDIP: A Unified Deep Framework for Low-light Image Enhancement," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3073371.

Install

Files Structure

├─data │ ├─test ├─net ├─output │ ├─illumination │ └─reflection ├─result └─utils

Dataset

Experiments

python Retinexdip.py --input data/test --result ./result

Before running the code, you must assure that every dataset is included in the input root directory. For example, these datasets should be included in the "./data/test":

datasets = ['DICM', 'ExDark', 'Fusion', 'LIME', 'NPEA', 'Nasa', 'VV']

Explanations for some hyperparameters: