HazeFlow : Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing (ICCV2025)

<div style="display: flex; justify-content: space-between; align-items: baseline;"> <h2 style="color: gray; margin: 0;">Authors </h2> </div> <h3 style="margin-top: 0;"> <a href="https://junsung6140.github.io/">Junseong Shin*</a>, <a href="https://cloor.github.io/">Seungwoo Chung*</a>, Yunjeong Yang, <a href="https://sites.google.com/view/lliger9">Tae Hyun Kim<sup>†</sup></a> </h3> <h4><sub><sup>(* denotes equal contribution. <sup>†</sup> denotes corresponding author.)</sup></sub></h4> <p align="center"> <img src="assets/ASM5.png" alt="hazeflow" width="800"/> </p>

This is the official implementation of ICCV2025 "HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing" [paper] / [project page]

Results

More qualitative and quantitative results can be found on the [project page].

📦 Installation

git clone https://github.com/cloor/HazeFlow.git
cd HazeFlow
pip install -r requirements.txt

git clone https://github.com/cloor/HazeFlow.git
cd HazeFlow
conda env create -f environment.yaml

Checkpoints can be downloaded here.

Visual Results can be downloaded here.

🌫️ Haze Generation

<p align="center"> <img src="assets/mcbm.png" alt="mcbm" width="800"/> <br> <b>Figure:</b> Example of non-homogeneous haze synthesized via MCBM. (a) Generated hazy image. (b) Transmission map <code>T<sub>MCBM</sub></code>. (c) Spatially varying density coefficient map <code>𝛽̃</code>. </p>

You can generate haze density maps using MCBM by running the command below:

python haze_generation/brownian_motion_generation.py

🏋️ Training

📁 Dataset Preparation

Please download and organize the datasets as follows:

| Dataset | Description | Download Link | |-----------|---------------------------------------------------------|----------------| | RIDCP500 | 500 clear RGB images | rgb_500 / da_depth_500 | | RTTS | Real-world task-driven testing set | Link | | URHI | Urban and rural haze images (duplicate-removed version) | Link |

HazeFlow/
├── datasets/
│   ├── RIDCP500/  
│   │   ├── rgb_500/
│   │   ├── da_depth_500/
│   │   ├── MCBM/
│   ├── RTTS/  
│   ├── URHI/           
│   └── custom/

Before training, make sure the datasets are properly structured as shown above.
Additionally, prepare the MCBM-based haze density maps and corresponding depth maps.

To estimate depth maps, follow the instructions provided in the Depth Anything V2 repository and place the depth maps in the datasets/RIDCP500/da_depth_500/ directory.

Once depth maps are ready, you can proceed to training and inference as described below.

1. Pretrain Phase

We propose using a color loss to reduce color distortion.
You can configure the loss type by editing --config.training.loss_type in pretrain.sh.

sh pretrain.sh

2. Reflow Phase

Specify the pretrained checkpoint from the pretrain phase by editing --config.flow.pre_train_model in reflow.sh.

sh reflow.sh

3. Distillation Phase

Specify the checkpoint obtained from the reflow phase by editing --config.flow.pre_train_model in distill.sh.

sh distill.sh

Inference & Demo

To run inference on your own images, place them in the dataset/custom/ directory.

Then, configure the following options in sampling.sh:

--config.sampling.ckpt: path to your trained model checkpoint
--config.data.dataset: name of your dataset (rtts or custom)
--config.data.test_data_root: path to your input images

Finally, run:

sh sampling.sh

🔗 Acknowledgements

Our implementation is based on RectifiedFlow and SlimFlow. We sincerely thank the authors for their contributions to the community.

📚 Citation

If you use this code or find our work helpful, please cite our paper:

@inproceedings{shin2025hazeflow,
  title={HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing},
  author={Shin, Junseong and Chung, Seungwoo and Yang, Yunjeong and Kim, Tae Hyun},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={6263--6272},
  year={2025}
}

Contact

If you have any questions, please contact junsung6140@hanyang.ac.kr.

HazeFlow

Install / Use

README