MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks

In applications such as satellite remote sensing and aerial photography, imaging equipment must capture brightness information of different ground scenes within a restricted dynamic range. Due to camera sensor limitations, captured images can represent only a portion of such information, which resul...

Full description

Saved in:
Bibliographic Details
Main Authors: Sibo Yu, Kun Wu, Guang Zhang, Wanhong Yan, Xiaodong Wang, Chen Tao
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/18/3501
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259698546114560
author Sibo Yu
Kun Wu
Guang Zhang
Wanhong Yan
Xiaodong Wang
Chen Tao
author_facet Sibo Yu
Kun Wu
Guang Zhang
Wanhong Yan
Xiaodong Wang
Chen Tao
author_sort Sibo Yu
collection DOAJ
description In applications such as satellite remote sensing and aerial photography, imaging equipment must capture brightness information of different ground scenes within a restricted dynamic range. Due to camera sensor limitations, captured images can represent only a portion of such information, which results in lower resolution and lower dynamic range compared with real scenes. Image super resolution (SR) and multiple-exposure image fusion (MEF) are commonly employed technologies to address these issues. Nonetheless, these two problems are often researched in separate directions. In this paper, we propose MEFSR-GAN: an end-to-end framework based on generative adversarial networks that simultaneously combines super-resolution and multiple-exposure fusion. MEFSR-GAN includes a generator and two discriminators. The generator network consists of two parallel sub-networks for under-exposure and over-exposure, each containing a feature extraction block (FEB), a super-resolution block (SRB), and several multiple-exposure feedback blocks (MEFBs). It processes low-resolution under- and over-exposed images to produce high-resolution high dynamic range (HDR) images. These images are evaluated by two discriminator networks, driving the generator to generate realistic high-resolution HDR outputs through multi-goal training. Extensive qualitative and quantitative experiments were conducted on the SICE dataset, yielding a PSNR of 24.821 and an SSIM of 0.896 for 2× upscaling. These results demonstrate that MEFSR-GAN outperforms existing methods in terms of both visual effects and objective evaluation metrics, thereby establishing itself as a state-of-the-art technology.
format Article
id doaj-art-41ed2bca8e1c47f59d8c1aa059dd78ca
institution OA Journals
issn 2072-4292
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-41ed2bca8e1c47f59d8c1aa059dd78ca2025-08-20T01:55:49ZengMDPI AGRemote Sensing2072-42922024-09-011618350110.3390/rs16183501MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial NetworksSibo Yu0Kun Wu1Guang Zhang2Wanhong Yan3Xiaodong Wang4Chen Tao5Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaIn applications such as satellite remote sensing and aerial photography, imaging equipment must capture brightness information of different ground scenes within a restricted dynamic range. Due to camera sensor limitations, captured images can represent only a portion of such information, which results in lower resolution and lower dynamic range compared with real scenes. Image super resolution (SR) and multiple-exposure image fusion (MEF) are commonly employed technologies to address these issues. Nonetheless, these two problems are often researched in separate directions. In this paper, we propose MEFSR-GAN: an end-to-end framework based on generative adversarial networks that simultaneously combines super-resolution and multiple-exposure fusion. MEFSR-GAN includes a generator and two discriminators. The generator network consists of two parallel sub-networks for under-exposure and over-exposure, each containing a feature extraction block (FEB), a super-resolution block (SRB), and several multiple-exposure feedback blocks (MEFBs). It processes low-resolution under- and over-exposed images to produce high-resolution high dynamic range (HDR) images. These images are evaluated by two discriminator networks, driving the generator to generate realistic high-resolution HDR outputs through multi-goal training. Extensive qualitative and quantitative experiments were conducted on the SICE dataset, yielding a PSNR of 24.821 and an SSIM of 0.896 for 2× upscaling. These results demonstrate that MEFSR-GAN outperforms existing methods in terms of both visual effects and objective evaluation metrics, thereby establishing itself as a state-of-the-art technology.https://www.mdpi.com/2072-4292/16/18/3501multitask networkssuper resolutionmultiple exposure fusiongenerative adversarial networks
spellingShingle Sibo Yu
Kun Wu
Guang Zhang
Wanhong Yan
Xiaodong Wang
Chen Tao
MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks
Remote Sensing
multitask networks
super resolution
multiple exposure fusion
generative adversarial networks
title MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks
title_full MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks
title_fullStr MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks
title_full_unstemmed MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks
title_short MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks
title_sort mefsr gan a multi exposure feedback and super resolution multitask network via generative adversarial networks
topic multitask networks
super resolution
multiple exposure fusion
generative adversarial networks
url https://www.mdpi.com/2072-4292/16/18/3501
work_keys_str_mv AT siboyu mefsrganamultiexposurefeedbackandsuperresolutionmultitasknetworkviagenerativeadversarialnetworks
AT kunwu mefsrganamultiexposurefeedbackandsuperresolutionmultitasknetworkviagenerativeadversarialnetworks
AT guangzhang mefsrganamultiexposurefeedbackandsuperresolutionmultitasknetworkviagenerativeadversarialnetworks
AT wanhongyan mefsrganamultiexposurefeedbackandsuperresolutionmultitasknetworkviagenerativeadversarialnetworks
AT xiaodongwang mefsrganamultiexposurefeedbackandsuperresolutionmultitasknetworkviagenerativeadversarialnetworks
AT chentao mefsrganamultiexposurefeedbackandsuperresolutionmultitasknetworkviagenerativeadversarialnetworks