Skip to content

About

aswe

Resources

Stars

7 stars

Watchers

1 watching

Forks

Latest commit

 

History

26 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

!!!!!Under construction!!!!

Single Image Denoising via a New Lightweight Learning-Based Model

SADJAD REZVANI1, FATEMEH SOLEYMANI SIAHKAR2, YASIN REZVANI3, ABDORREZAALAVI GHARAHBAGH4, AND VAHID ABOLGHASEMI

In this work, we tackle the complex challenge of image denoising, especially in scenarios where high-resolution images are corrupted by noise, making it difficult to restore their quality. Our proposed Fast Residual Denoising Framework (FRDF) leverages zero-shot learning principles, allowing it to effectively denoise images without the need for clean/noisy image pairs for training. With only 23K parameters, our model is lightweight and efficient, making it suitable for real-world applications ranging from medical imaging to surveillance, even with limited computational resources.

Network Architecture

main

Installation

how to install NOT excited reqirement.txt

python 3.6.9
git clone https://github.com/sadjadrz/Zero-shot-image-denoising-based-on-downsampling

Quick Start (Single Image Inference)


  • python basicsr/demo.py -opt options/demo/demo.yml
    • modified your

Results


image

License

This project is under the MIT license.

Citations

@article{rezvani2024single,
  title={Single Image Denoising via a New Lightweight Learning-Based Model},
  author={Rezvani, Sadjad and Siahkar, Fatemeh Soleymani and Rezvani, Yasin and Gharahbagh, Abdorreza Alavi and Abolghasemi, Vahid},
  journal={IEEE Access},
  year={2024},
  publisher={IEEE}
}

Contact

If you have any questions, please contact [email protected].

About

aswe

Resources

Stars

7 stars

Watchers

1 watching

Forks

Contributors

Languages