Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV

PyTorch implementation for 《Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV》

:rocket::rocket::rocket:Check our paper collection of recent Awsome-RWKV-in-Vision

:rocket::rocket::rocket:Check our paper collection of recent Awsome-Medical-Image-Restoration

Network Architecture

Visualization

Dataset

You can download the preprocessed datasets for MRI image super-resolution, CT image denoising, and PET image synthesis from Baidu Netdisk or Google Drive.

The original dataset for MRI super-resolution and CT denoising are as follows:

• MRI super-resolution: IXI dataset

• CT denoising: AAPM dataset

Citation

If you find Restore-RWKV useful in your research, please consider citing:

@article{yang2026restorerwkv,
  title={Restore-rwkv: Efficient and effective medical image restoration with rwkv},
  author={Yang, Zhiwen and Li, Jiayin and Zhang, Hui and Zhao, Dan and Wei, Bingzheng and Xu, Yan},
  journal={IEEE Journal of Biomedical and Health Informatics},
  year={2026},
  volume={30},
  number={1},
  pages={513-526},
  publisher={IEEE}
}