This is the official repository for the paper 📄 "SeaDiff: Underwater Image Enhancement with Degradation-Aware Diffusion Model".
- 2025.06.15: The initial version of the code is uploaded.
- Python = 3.9
- PyTorch = 2.0.0
- torchvision = 0.15.1
- CUDA = 11.7
# Clone the repository
git clone https://github.com/yourusername/SeaDiff.git
cd SeaDiff
# Create conda environment
conda create -n seadiff python=3.8
conda activate seadiffTo train SeaDiff, please follow these steps:
-
Download UIE datasets:
-
Generate depth maps using Depth Anything V2:
-
Create histogram representations:
python utils/create_hist_sample.py --input_dir datasets/UIEB/train/input --output_dir datasets/UIEB/train/histo
After preprocessing, organize your data as follows:
datasets/
└── UIEB/
├── train/
│ ├── input/
│ ├── label/
│ ├── depth/
│ └── histo/
└── val/
├── input/
├── label/
├── depth/
└── histo/
-
Modify the configuration in
conf.yml:MODE: 1 # 1 for training, 0 for inference PRE_ORI: 'True' # True for $x_0$, False for $\epsilon$ # ... other parameters
-
Start:
python main.py --conf conf.yml
If you find our work useful, please cite:
@ARTICLE{11062889,
author={Bi, Hengyue and Chen, Long and Cao, Jingchao and Wang, Jingyang and Sun, Jinghao and Rao, Yuan and Dong, Junyu},
journal={IEEE Transactions on Circuits and Systems for Video Technology},
title={SeaDiff: Underwater Image Enhancement with Degradation-Aware Diffusion Model},
year={2025},
volume={},
number={},
pages={1-1},
keywords={Image color analysis;Diffusion models;Degradation;Training;Imaging;Adaptation models;Image enhancement;Histograms;Feature extraction;Data mining;Underwater image enhancement;conditional diffusion models;prior knowledge},
doi={10.1109/TCSVT.2025.3585429}}
Our code is based on the following excellent works:
We thank the authors for their outstanding contributions! 🙏
If you have any questions, please feel free to:
- 📧 Email: [email protected]
- 🐛 Open an Issue
- 💬 Start a Discussion
⭐ If you find this project helpful, please consider giving it a star! ⭐