Image Super-Resolution Algorithm Based on RRDB Model

Aiming at the problems of texture distortion and fuzzy details in the existing image super-resolution reconstruction methods, a super-resolution reconstruction network based on multi-channel attention mechanism is proposed. The texture extraction module designs an extremely lightweight multi-channel...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Huan Li
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Image super-resolution reconstruction texture migration attention mechanism one-dimensional convolution dense residual block Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/32b77e617b894d0fa287d908f2f39e3b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:32b77e617b894d0fa287d908f2f39e3b
record_format	dspace
spelling	oai:doaj.org-article:32b77e617b894d0fa287d908f2f39e3b2021-12-01T00:01:31ZImage Super-Resolution Algorithm Based on RRDB Model2169-353610.1109/ACCESS.2021.3118444https://doaj.org/article/32b77e617b894d0fa287d908f2f39e3b2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9562515/https://doaj.org/toc/2169-3536Aiming at the problems of texture distortion and fuzzy details in the existing image super-resolution reconstruction methods, a super-resolution reconstruction network based on multi-channel attention mechanism is proposed. The texture extraction module designs an extremely lightweight multi-channel attention module in the network structure. Combined with one-dimensional convolution, it realizes cross-channel information interaction, focusing on important feature information; The texture restoration module introduces dense remaining blocks to restore some high-frequency texture details, improve the model performance, and generate high-quality reconstructed images. The proposed network can not only effectively improve the visual effect of the image, but the results on the benchmark data set CUFED5 are similar to the classic super-resolution (SRCNN) reconstruction method based on convolutional neural network. The peak signal-to-noise ratio (PSNR) and structure are similar. Degrees (SSIM) increased by 1.76dB and 0.062 respectively. Experimental results show that the designed network can improve the accuracy of texture migration and can effectively improve the quality of the generated image.Huan LiIEEEarticleImage super-resolution reconstructiontexture migrationattention mechanismone-dimensional convolutiondense residual blockElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 156260-156273 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Image super-resolution reconstruction texture migration attention mechanism one-dimensional convolution dense residual block Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Image super-resolution reconstruction texture migration attention mechanism one-dimensional convolution dense residual block Electrical engineering. Electronics. Nuclear engineering TK1-9971 Huan Li Image Super-Resolution Algorithm Based on RRDB Model
description	Aiming at the problems of texture distortion and fuzzy details in the existing image super-resolution reconstruction methods, a super-resolution reconstruction network based on multi-channel attention mechanism is proposed. The texture extraction module designs an extremely lightweight multi-channel attention module in the network structure. Combined with one-dimensional convolution, it realizes cross-channel information interaction, focusing on important feature information; The texture restoration module introduces dense remaining blocks to restore some high-frequency texture details, improve the model performance, and generate high-quality reconstructed images. The proposed network can not only effectively improve the visual effect of the image, but the results on the benchmark data set CUFED5 are similar to the classic super-resolution (SRCNN) reconstruction method based on convolutional neural network. The peak signal-to-noise ratio (PSNR) and structure are similar. Degrees (SSIM) increased by 1.76dB and 0.062 respectively. Experimental results show that the designed network can improve the accuracy of texture migration and can effectively improve the quality of the generated image.
format	article
author	Huan Li
author_facet	Huan Li
author_sort	Huan Li
title	Image Super-Resolution Algorithm Based on RRDB Model
title_short	Image Super-Resolution Algorithm Based on RRDB Model
title_full	Image Super-Resolution Algorithm Based on RRDB Model
title_fullStr	Image Super-Resolution Algorithm Based on RRDB Model
title_full_unstemmed	Image Super-Resolution Algorithm Based on RRDB Model
title_sort	image super-resolution algorithm based on rrdb model
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/32b77e617b894d0fa287d908f2f39e3b
work_keys_str_mv	AT huanli imagesuperresolutionalgorithmbasedonrrdbmodel
_version_	1718406131304366080

Image Super-Resolution Algorithm Based on RRDB Model

Ejemplares similares