Home

Awesome

<div align="center">

【AAAI'2024】Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement

</div>

The official implementation of AAAI24 paper Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement.

Environment

create a new conda env, and run

$ pip install -r requirements.txt

torch/torchvision with CUDA version >= 11.3 should be fine.

Demo

1. Download pretrained model

Download the Pretrained MDMS model from Baidu NetDisk or Google Drive.

Put the downloaded ckpt in datasets/scratch/LLIE/ckpts.

2. Inference

# in {path_to_this_repo}/,
$ python eval_diffusion.py

Put the test input in datasets/scratch/LLIE/data/lowlight/test/input.

Output results will be saved in results/images/lowlight/lowlight.

Evaluation

Put the test GT in datasets/scratch/LLIE/data/lowlight/test/gt for paired evaluation.

# in {path_to_this_repo}/,
$ python evaluation.py

Results

All results listed in our paper including the compared methods are available in Baidu Netdisk or Google Drive.

Our method remains superior under the same setting as PyDiff.

<div align="center"> <img src="figs/com.png" width="600"/> </div>

1. Test results on LOLv1 test set.

<div align="center"> <img src="figs/v1.png" width="800"/> </div>

2. Generalization results on LOLv2 syn and real test sets.

<div align="center"> <img src="figs/vis.png" width="800"/> </div>

3. Generalization results on other unpaired datasets.

<div align="center"> <img src="figs/unpaired.png" width="600"/> </div>

We will perform more training and tests on other datasets in the future.

Training

Put the training dataset in datasets/scratch/LLIE/data/lowlight/train.

# in {path_to_this_repo}/,
$ python train_diffusion.py

Detailed training instructions will be updated soon.

Citation

If you find this paper useful, please consider staring this repo and citing our paper:

@inproceedings{shang2024multi,
  title={Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement},
  author={Shang, Kai and Shao, Mingwen and Wang, Chao and Cheng, Yuanshuo and Wang, Shuigen},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={38},
  number={5},
  pages={4722--4730},
  year={2024}
}