Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion [Paper].

Introduction

In this repo, we propose a novel and robust low-light image enhancement method, named CFWD. Extensive experiments on publicly available real-world benchmarks show that our method outperforms existing SOTA methods quantitatively and visually, maximizing image restoration similar to normal images. For more details, please refer to our paper link

Project Setup

Clone Repo

git clone https://github.com/He-Jinhong/CFWD.git
cd CFWD  

Create Conda Environment and Install Dependencies:

pip install -r requirements.txt

Download the raw training and evaluation datasets

[Google Drive]

Pre-trained Models

You can downlaod our pre-training prompts and pre-training models from [Google Drive]

Quick Inference

Before performing the following steps, please download our pretrained model first. You need to modify test.py and datasets.py according to your environment and then

python test.py

Train

We will re-update soon.

Results on Low-light Image Enhancement

Citation

@article{10.1145/3764933,
author = {Xue, Minglong and He, Jinhong and Wang, Wenhai and Zhou, Mingliang},
title = {Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion},
year = {2025},
issn = {1551-6857},
url = {https://doi.org/10.1145/3764933},
doi = {10.1145/3764933},
journal = {ACM Trans. Multimedia Comput. Commun. Appl.}
}

Acknowledgement

Our underlying network comes from previous works: WCDM. We thanks the authors for their contributions.