Multi-scale Xception based depthwise separable convolution for single image super-resolution.

The main target of Single image super-resolution is to recover high-quality or high-resolution image from degraded version of low-quality or low-resolution image. Recently, deep learning-based approaches have achieved significant performance in image super-resolution tasks. However, existing approac...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wazir Muhammad, Supavadee Aramvith, Takao Onoye
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/2fe902e341ae403db0d00aae30ccb45c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2fe902e341ae403db0d00aae30ccb45c
record_format	dspace
spelling	oai:doaj.org-article:2fe902e341ae403db0d00aae30ccb45c2021-12-02T20:14:56ZMulti-scale Xception based depthwise separable convolution for single image super-resolution.1932-620310.1371/journal.pone.0249278https://doaj.org/article/2fe902e341ae403db0d00aae30ccb45c2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0249278https://doaj.org/toc/1932-6203The main target of Single image super-resolution is to recover high-quality or high-resolution image from degraded version of low-quality or low-resolution image. Recently, deep learning-based approaches have achieved significant performance in image super-resolution tasks. However, existing approaches related with image super-resolution fail to use the features information of low-resolution images as well as do not recover the hierarchical features for the final reconstruction purpose. In this research work, we have proposed a new architecture inspired by ResNet and Xception networks, which enable a significant drop in the number of network parameters and improve the processing speed to obtain the SR results. We are compared our proposed algorithm with existing state-of-the-art algorithms and confirmed the great ability to construct HR images with fine, rich, and sharp texture details as well as edges. The experimental results validate that our proposed approach has robust performance compared to other popular techniques related to accuracy, speed, and visual quality.Wazir MuhammadSupavadee AramvithTakao OnoyePublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 8, p e0249278 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Wazir Muhammad Supavadee Aramvith Takao Onoye Multi-scale Xception based depthwise separable convolution for single image super-resolution.
description	The main target of Single image super-resolution is to recover high-quality or high-resolution image from degraded version of low-quality or low-resolution image. Recently, deep learning-based approaches have achieved significant performance in image super-resolution tasks. However, existing approaches related with image super-resolution fail to use the features information of low-resolution images as well as do not recover the hierarchical features for the final reconstruction purpose. In this research work, we have proposed a new architecture inspired by ResNet and Xception networks, which enable a significant drop in the number of network parameters and improve the processing speed to obtain the SR results. We are compared our proposed algorithm with existing state-of-the-art algorithms and confirmed the great ability to construct HR images with fine, rich, and sharp texture details as well as edges. The experimental results validate that our proposed approach has robust performance compared to other popular techniques related to accuracy, speed, and visual quality.
format	article
author	Wazir Muhammad Supavadee Aramvith Takao Onoye
author_facet	Wazir Muhammad Supavadee Aramvith Takao Onoye
author_sort	Wazir Muhammad
title	Multi-scale Xception based depthwise separable convolution for single image super-resolution.
title_short	Multi-scale Xception based depthwise separable convolution for single image super-resolution.
title_full	Multi-scale Xception based depthwise separable convolution for single image super-resolution.
title_fullStr	Multi-scale Xception based depthwise separable convolution for single image super-resolution.
title_full_unstemmed	Multi-scale Xception based depthwise separable convolution for single image super-resolution.
title_sort	multi-scale xception based depthwise separable convolution for single image super-resolution.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/2fe902e341ae403db0d00aae30ccb45c
work_keys_str_mv	AT wazirmuhammad multiscalexceptionbaseddepthwiseseparableconvolutionforsingleimagesuperresolution AT supavadeearamvith multiscalexceptionbaseddepthwiseseparableconvolutionforsingleimagesuperresolution AT takaoonoye multiscalexceptionbaseddepthwiseseparableconvolutionforsingleimagesuperresolution
_version_	1718374635797479424

Multi-scale Xception based depthwise separable convolution for single image super-resolution.

Ejemplares similares