Guardado en:
Detalles Bibliográficos
Autores principales: Pham, Ngoc-Giau, Le, Thanh-Hai Tong, Duong, Van-Hieu, Tran, Hong-Ngoc, Vo, Phuoc-Hung
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2404.09817
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911916638601216
author Pham, Ngoc-Giau
Le, Thanh-Hai Tong
Duong, Van-Hieu
Tran, Hong-Ngoc
Vo, Phuoc-Hung
author_facet Pham, Ngoc-Giau
Le, Thanh-Hai Tong
Duong, Van-Hieu
Tran, Hong-Ngoc
Vo, Phuoc-Hung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09817
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Problem Of Image Super-Resolution, Denoising And Some Image Restoration Methods In Deep Learning Models
Pham, Ngoc-Giau
Le, Thanh-Hai Tong
Duong, Van-Hieu
Tran, Hong-Ngoc
Vo, Phuoc-Hung
Disordered Systems and Neural Networks
Dynamical Systems
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.
title The Problem Of Image Super-Resolution, Denoising And Some Image Restoration Methods In Deep Learning Models
topic Disordered Systems and Neural Networks
Dynamical Systems
url https://arxiv.org/abs/2404.09817