StainRestorer

KO | EN

gitlite — search

#python #java #python3 #arduino #golang #machine-learning #rust #html #flask #javascript #seismology #nodejs

★ 24 Open GitHub ↗

[WACV 2025] High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# StainRestorer

[**High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer**](https://arxiv.org/abs/2410.22922)

<div>

 Mingxian Li 👨‍💻‍ 
,
 
 Hao Sun 👨‍💻‍ 
 ,
 
 Yingtie Lei 👨‍💻‍ 
 ,
 
 <a href='https://zhangbaijin.github.io/'>Xiaofeng Zhang</a>
 ,
 
 Yihang Dong
 ,
 
 Yilin Zhou
 ,
 
 Zimeng Li
 ,
 
 <a href='https://cxh.netlify.app/'>Xuhang Chen</a> 📮

 ( 👨‍💻‍ Equal contributions, 📮 Corresponding author)
</div>

Huizhou Univeristy, University of Macau, Shanghai Jiao Tong University, SIAT CAS, Shenzhen Polytechnic University

In _IEEE/CVF Winter Conference on Applications of Computer Vision 2025 (WACV 2025)_

# 🔮 Dataset

[Kaggle](https://www.kaggle.com/datasets/xuhangc/wacv2025-staindoc)

StainDoc is the first large-scale high-resolution dataset that includes ground truth data specifically for the task of document stain removal.

StainDoc_mark and StainDoc_seal are made with the process in [DocDiff](https://github.com/Royalvice/DocDiff).

# ⚙️ Usage

## Training
You may download the dataset first, and then specify TRAIN_DIR, VAL_DIR and SAVE_DIR in the section TRAINING in `config.yml`.

For single GPU training:
```
python train.py
```
For multiple GPUs training:
```
accelerate config
accelerate launch train.py
```
If you have difficulties with the usage of `accelerate`, please refer to <a href="https://github.com/huggingface/accelerate">Accelerate</a>.

## Inference

Please download our pre-trained models [here](https://github.com/CXH-Research/StainRestorer/releases/tag/Weights) and specify TRAIN_DIR, VAL_DIR and SAVE_DIR in section TESTING in `config.yml`.

```bash
python infer.py
```

# Citation

```bib
@inproceedings{li2025high,
  title={High-fidelity document stain removal via a large-scale real-world dataset and a memory-augmented transformer},
  author={Li, Mingxian and Sun, Hao and Lei, Yingtie and Zhang, Xiaofeng and Dong, Yihang and Zhou, Yilin and Li, Zimeng and Chen, Xuhang},
  booktitle={2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  pages={7614--7624},
  year={2025},
  organization={IEEE}
}
```

StainRestorer

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README