DM2F-Net

By Zijun Deng, Lei Zhu, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Qing Zhang, Jing Qin, and Pheng-Ann Heng.

This repo is the implementation of "Deep Multi-Model Fusion for Single-Image Dehazing" (ICCV 2019), written by Zijun Deng at the South China University of Technology.

代码使用方法

1.对于自己收集的数据，创建data文件夹后把Self文件夹放入其中。 2.train_ohaze和test_ohaze都是针对ohaze数据集，test_self针对自己搜集数据，其中可以选择四种模型，需要根据不同的模型改代码中的“net = ”部分。 3.model文件中convnext_base需要提前下载缓存后，修改加载路径

模型权重下载：链接：https://pan.baidu.com/s/1Vj1_4E13RkCdPaw_mVLJWA 提取码：7f1e

Results

The dehazing results can be found at Google Drive.

Installation & Preparation

Make sure you have Python>=3.7 installed on your machine.

Environment setup:

Create conda environment

conda create -n dm2f
conda activate dm2f

Install dependencies (test with PyTorch 1.8.0):
1. Install pytorch==1.8.0 torchvision==0.9.0 (via conda, recommend).
2. Install other dependencies
```
pip install -r requirements.txt
```

Prepare the dataset
- Download the RESIDE dataset from the official webpage.
- Download the O-Haze dataset from the official webpage.
- Make a directory ./data and create a symbolic link for uncompressed data, e.g., ./data/RESIDE.

Training

~~Set the path of pretrained ResNeXt model in resnext/config.py~~
Set the path of datasets in tools/config.py
Run by python train.py

~~The pretrained ResNeXt model is ported from the official torch version, using the convertor provided by clcarwin. You can directly download the pretrained model ported by me.~~

Use pretrained ResNeXt (resnext101_32x8d) from torchvision.

Hyper-parameters of training were set at the top of train.py, and you can conveniently change them as you need.

Training a model on a single ~~GTX 1080Ti~~ TITAN RTX GPU takes about 4 5 hours.

Testing

Set the path of five benchmark datasets in tools/config.py.
Put the trained model in ./ckpt/.
Run by python test.py

Settings of testing were set at the top of test.py, and you can conveniently change them as you need.

License

DM2F-Net is released under the MIT license.

Citation

If you find the paper or the code helpful to your research, please cite the project.

@inproceedings{deng2019deep,
  title={Deep multi-model fusion for single-image dehazing},
  author={Deng, Zijun and Zhu, Lei and Hu, Xiaowei and Fu, Chi-Wing and Xu, Xuemiao and Zhang, Qing and Qin, Jing and Heng, Pheng-Ann},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={2453--2462},
  year={2019}
}

SresserS/Improved-DMMF