!!!!!Under construction!!!!
SADJAD REZVANI1, FATEMEH SOLEYMANI SIAHKAR2, YASIN REZVANI3, ABDORREZAALAVI GHARAHBAGH4, AND VAHID ABOLGHASEMI
Paper: [https://ieeexplore.ieee.org/iel8/6287639/6514899/10654252.pdf]
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.
how to install NOT excited reqirement.txt
python 3.6.9git clone https://github.com/sadjadrz/Zero-shot-image-denoising-based-on-downsampling
python basicsr/demo.py -opt options/demo/demo.yml- modified your
This project is under the MIT license.
@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}
}
If you have any questions, please contact [email protected].

