weichen582/RetinexNet
A TensorFlow implementation of RetinexNet, a deep learning model for low-light image enhancement.

Velocity · 7d
+0.3
★ / day
Trend
→steady
star history
This repository provides a TensorFlow implementation of RetinexNet from the BMVC 2018 paper ‘Deep Retinex Decomposition for Low-Light Enhancement’. The model decomposes low-light images into reflectance and illumination components to produce enhanced results. It includes training and testing scripts with GPU support, configurable hyperparameters, and uses a custom LOL dataset for training.