The Problem Of Image Super-Resolution, Denoising And Some Image Restoration Methods In Deep Learning Models
Abstract
In this article, we address the challenges of image super-resolution and noise reduction, which are crucial for enhancing the quality of images derived from low-resolution or noisy data. We compared and assessed several approaches for upgrading low-resolution images to higher resolutions and for eliminating unwanted noise, all while maintaining the essential characteristics of the original images and recovering images from poor quality or damaged data using deep learning models. Our analysis and the experimental outcomes on image quality metrics indicate that the EDCNN neural network model, enhanced with pretrained weights, significantly outperforms other methods with a Train PSNR of 31.215, a Valid PSNR of 29.493, and a Test PSNR of 31.6632.
Cite
@article{arxiv.2404.09817,
title = {The Problem Of Image Super-Resolution, Denoising And Some Image Restoration Methods In Deep Learning Models},
author = {Ngoc-Giau Pham and Thanh-Hai Tong Le and Van-Hieu Duong and Hong-Ngoc Tran and Phuoc-Hung Vo},
journal= {arXiv preprint arXiv:2404.09817},
year = {2024}
}
Comments
This article is no longer relevant