[MS2025] ALEN: A Dual-Approach for Uniform and Non-Uniform Low-Light Image Enhancement

Ezequiel Perez-Zarate. Oscar Ramos-Soto, Chunxiao Liu, Diego Oliva, Marco Perez-Cisneros

🎯 1. Overview

This repository contains the source code and supplementary materials for the paper "ALEN: A Dual-Approach for Uniform and Non-Uniform Low-Light Image Enhancement". The research focuses on enhancing low-light images and has been accepted for publication in the Multimedia Systems journal, published by Springer.

🛠️ 2. Requirements

1. opencv-python == 4.9.0.80
2. scikit-image == 0.22.0
3. numpy == 1.24.3
4. torch == 2.3.0+cu118
5. Pillow == 10.2.0
6. tqdm == 4.65.0
7. natsort == 8.4.0
8. torchvision == 0.18.0+cu118

🧪 3. Inference

To test the model, follow these steps:

1. Download the pretrained weights from either of the following links, and place them in the ./Models directory:

   • Google Drive
   • OneDrive

2. Place your images to be enhanced in the ./1_Input directory.

3. Run the code with the following command:

   python inference.py
   

4. The enhanced images will be saved in the ./2_Output directory.

🗂️ 4. Datasets

This section describes the datasets used to train and evaluate the performance of ALEN: Adaptive Light Enhancement Network for low-light image enhancement.

📚 4.1. Training Datasets

The following public datasets were used to train the ALEN model. These datasets contain images with global and local illumination variations, necessary for effective classification and enhancement:

Dataset	Description	Number of Images	Type	Resources
GLI	Global-Local Illumination	2,000	Paired Classification	Dataset
HDR+	High Dynamic Range Plus	922	Paired Enhancement	Paper/Dataset
SLL	Synthetic Low-Light	22,472	Paired Enhancement	Paper/Dataset
MIT	MIT-Adobe FiveK	5,000	Paired Enhancement	Paper/Dataset

🧾 4.2. Evaluation Datasets

To evaluate the overall performance and generalization ability of ALEN, we used various datasets representing real-world scenarios:

Dataset	Description	Number of Images	Type	Resources
DIS	Diverse Illumination Scene	10	Unpaired Enhancement	Dataset

📄 Citation

If this work contributes to your research, we would appreciate it if you could cite our paper:

@article{perez2025alen,
  title={ALEN: a dual-approach for uniform and non-uniform low-light image enhancement},
  author={Perez-Zarate, Ezequiel and Ramos-Soto, Oscar and Liu, Chunxiao and Oliva, Diego and Perez-Cisneros, Marco},
  journal={Multimedia Systems},
  volume={31},
  number={3},
  pages={1--23},
  year={2025},
  publisher={Springer}
}