README.md

---
license: apache-2.0
language:
- en
base_model:
- prs-eth/marigold-depth-v1-0
- stabilityai/stable-diffusion-2
tags:
- underwater restoration
- latent diffusion model
- image analysis
- computer vision
library_name: diffusers
---
<h1 align="center">SLURPP Single-Step Latent Diffusion Underwater Restoration</h1>


<p align="center">
</a>
<a title="Website" href="https://tianfwang.github.io/slurpp/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/%E2%99%A5%20Project%20-Website-blue" alt="Website">
</a>
<a title="arXiv" href="https://arxiv.org/abs/2507.07878" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/%F0%9F%93%84%20Read%20-Paper-AF3436" alt="arXiv">
</a>
<a title="Github" href="https://github.com/kongdai123/SLURPP" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/github/stars/kongdai123/SLURPP?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="Github">

<a title="License" href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/License-Apache--2.0-929292" alt="License">
</a>
</p>


This is a model card for the `slurpp` model for underwater image restoration and water medium estimation from a single image. 
The model is fine-tuned from both `stable-diffusion-2` [model](https://huggingface.co/stabilityai/stable-diffusion-2) and `marigold-depth-v1-0` [model](https://huggingface.co/prs-eth/marigold-depth-v1-0).

This model is based on the paper:

Jiayi Wu, Tianfu Wang, Md Abu Bakr Siddique, Md Jahidul Islam, Cornelia Fermuller, Yiannis Aloimonos, Christopher A. Metzler "Single-Step Latent Diffusion Underwater Restoration," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

### Using the model
Please follow the inference script in the [github repo](https://github.com/kongdai123/SLURPP).

## Model Details
- **Developed by:** [Jiayi Wu](https://jiayi-wu-leo.github.io/), [Tianfu Wang](https://tianfwang.github.io/), [Md Abu Bakr Siddique](https://www.linkedin.com/in/bbkrsddque/), [Md Jahidul Islam](https://jahid.ece.ufl.edu/), [Cornelia Fermuller](https://users.umiacs.umd.edu/~fermulcm/), [Yiannis Aloimonos](https://robotics.umd.edu/clark/faculty/350/Yiannis-Aloimonos), [Christopher A. Metzler](https://www.cs.umd.edu/people/metzler).
- **Model type:** Diffusion-based single image underwater restoration and water medium prediction
- **Language:** English.
- **License:** [Apache License License Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).
- **Model Description:** Given an input underwater image, our single-step latent diffusion method SLURPP jointly predicts the clear image, and the per-pixel underwater medium parameters, specifically the backscattering and transmission parameters. 
  - **Steps and scheduler**: Only one step is required with this model using trailing DDIM scheduler
  - **Outputs**:
    - **Clear**: The predicted clear image 
    - **Transmission/Illuminaiton**: The ammount of attenuation experienced by each object in the scene
    - **Backscattering**: The amount additive light from illumination (ambient sunlight or artificial lights) that is scattered by the water volume
- **Resources for more information:** [Project Website](https://tianfwang.github.io/slurpp/), [Paper](https://arxiv.org/abs/2507.07878), [Code](https://github.com/kongdai123/SLURPP).
- **Cite as:**

```bibtex
@article{wu2025single,
  title={Single-Step Latent Diffusion for Underwater Image Restoration},
  author={Wu, Jiayi and Wang, Tianfu and Siddique, Md Abu Bakr and Islam, Md Jahidul and Fermuller, Cornelia and Aloimonos, Yiannis and Metzler, Christopher A},
  journal={arXiv preprint arXiv:2507.07878},
  year={2025}
}
```