Cargando…
Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks
Convolutional neural networks have greatly improved the performance of image super-resolution. However, perceptual networks have problems such as blurred line structures and a lack of high-frequency information when reconstructing image textures. To mitigate these issues, a generative adversarial ne...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9394415/ https://www.ncbi.nlm.nih.gov/pubmed/35893009 http://dx.doi.org/10.3390/e24081030 |
_version_ | 1784771485048504320 |
---|---|
author | Yuan, Cao Deng, Kaidi Li, Chen Zhang, Xueting Li, Yaqin |
author_facet | Yuan, Cao Deng, Kaidi Li, Chen Zhang, Xueting Li, Yaqin |
author_sort | Yuan, Cao |
collection | PubMed |
description | Convolutional neural networks have greatly improved the performance of image super-resolution. However, perceptual networks have problems such as blurred line structures and a lack of high-frequency information when reconstructing image textures. To mitigate these issues, a generative adversarial network based on multiscale asynchronous learning is proposed in this paper, whereby a pyramid structure is employed in the network model to integrate high-frequency information at different scales. Our scheme employs a U-net as a discriminator to focus on the consistency of adjacent pixels in the input image and uses the LPIPS loss for perceptual extreme super-resolution with stronger supervision. Experiments on benchmark datasets and independent datasets Set5, Set14, BSD100, and SunHays80 show that our approach is effective in restoring detailed texture information from low-resolution images. |
format | Online Article Text |
id | pubmed-9394415 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93944152022-08-23 Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks Yuan, Cao Deng, Kaidi Li, Chen Zhang, Xueting Li, Yaqin Entropy (Basel) Article Convolutional neural networks have greatly improved the performance of image super-resolution. However, perceptual networks have problems such as blurred line structures and a lack of high-frequency information when reconstructing image textures. To mitigate these issues, a generative adversarial network based on multiscale asynchronous learning is proposed in this paper, whereby a pyramid structure is employed in the network model to integrate high-frequency information at different scales. Our scheme employs a U-net as a discriminator to focus on the consistency of adjacent pixels in the input image and uses the LPIPS loss for perceptual extreme super-resolution with stronger supervision. Experiments on benchmark datasets and independent datasets Set5, Set14, BSD100, and SunHays80 show that our approach is effective in restoring detailed texture information from low-resolution images. MDPI 2022-07-26 /pmc/articles/PMC9394415/ /pubmed/35893009 http://dx.doi.org/10.3390/e24081030 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yuan, Cao Deng, Kaidi Li, Chen Zhang, Xueting Li, Yaqin Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks |
title | Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks |
title_full | Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks |
title_fullStr | Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks |
title_full_unstemmed | Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks |
title_short | Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks |
title_sort | improving image super-resolution based on multiscale generative adversarial networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9394415/ https://www.ncbi.nlm.nih.gov/pubmed/35893009 http://dx.doi.org/10.3390/e24081030 |
work_keys_str_mv | AT yuancao improvingimagesuperresolutionbasedonmultiscalegenerativeadversarialnetworks AT dengkaidi improvingimagesuperresolutionbasedonmultiscalegenerativeadversarialnetworks AT lichen improvingimagesuperresolutionbasedonmultiscalegenerativeadversarialnetworks AT zhangxueting improvingimagesuperresolutionbasedonmultiscalegenerativeadversarialnetworks AT liyaqin improvingimagesuperresolutionbasedonmultiscalegenerativeadversarialnetworks |