MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN

<p dir="ltr">Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded wit...

Full description

Saved in:
Bibliographic Details
Main Author: Maria Siddiqua (17949149) (author)
Other Authors: Samir Brahim Belhaouari (16855434) (author), Naeem Akhter (17949152) (author), Aneela Zameer (17095214) (author), Javaid Khurshid (17949155) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513527499194368
author Maria Siddiqua (17949149)
author2 Samir Brahim Belhaouari (16855434)
Naeem Akhter (17949152)
Aneela Zameer (17095214)
Javaid Khurshid (17949155)
author2_role author
author
author
author
author_facet Maria Siddiqua (17949149)
Samir Brahim Belhaouari (16855434)
Naeem Akhter (17949152)
Aneela Zameer (17095214)
Javaid Khurshid (17949155)
author_role author
dc.creator.none.fl_str_mv Maria Siddiqua (17949149)
Samir Brahim Belhaouari (16855434)
Naeem Akhter (17949152)
Aneela Zameer (17095214)
Javaid Khurshid (17949155)
dc.date.none.fl_str_mv 2023-06-26T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2023.3289591
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/MACGAN_An_All-in-One_Image_Restoration_Under_Adverse_Conditions_Using_Multidomain_Attention-Based_Conditional_GAN/25205192
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Snow
Feature extraction
Rain
Image restoration
Image color analysis
Degradation
Clouds
Weather forecasting
Generative adversarial networks
Restoration
multidomain
adverse weather
navigation
aerial
marine
attention mechanism
dc.title.none.fl_str_mv MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded with blue-green tones and mud affecting marine navigation. Existing techniques in the literature typically focus on restoring specific degradations using separate models, leading to computational inefficiency. To address this, an all-in-one Multidomain Attention-based Conditional Generative Adversarial Network (MACGAN) is proposed to improve scene visibility for optimal ground, aerial, and marine navigation, using the same set of parameters across all domains. The MACGAN is a lightweight network with four encoder and decoder blocks and multiple attention blocks in between, which enhances the image restoration process by focusing on the most important features. To evaluate the effectiveness of MACGAN, extensive qualitative and quantitative comparisons are conducted with state-of-the-art image-to-image translation models, all-in-one adverse weather removal models, and single-effect removal models. The results highlight the superior performance of MACGAN in terms of scene visibility improvement and restoration quality. Additionally, MACGAN is tested on real-world unseen image domains, including smog, dust, fog, rain, snow, and lightning, further validating its generalizability and robustness. Furthermore, an ablation study is conducted to analyze the contributions of the discriminator and attention blocks within the MACGAN architecture. The results confirm that both components play significant roles in the effectiveness of MACGAN, with the discriminator ensuring adversarial training and the attention blocks effectively capturing and enhancing important image features.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="http://creativecommons.org/licenses/by/4.0" target="_blank">http://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3289591" target="_blank">https://dx.doi.org/10.1109/access.2023.3289591</a></p>
eu_rights_str_mv openAccess
id Manara2_2a26f2224356db678cbfd21e6e5c4ef3
identifier_str_mv 10.1109/access.2023.3289591
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25205192
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GANMaria Siddiqua (17949149)Samir Brahim Belhaouari (16855434)Naeem Akhter (17949152)Aneela Zameer (17095214)Javaid Khurshid (17949155)EngineeringElectrical engineeringElectronics, sensors and digital hardwareMaterials engineeringSnowFeature extractionRainImage restorationImage color analysisDegradationCloudsWeather forecastingGenerative adversarial networksRestorationmultidomainadverse weathernavigationaerialmarineattention mechanism<p dir="ltr">Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded with blue-green tones and mud affecting marine navigation. Existing techniques in the literature typically focus on restoring specific degradations using separate models, leading to computational inefficiency. To address this, an all-in-one Multidomain Attention-based Conditional Generative Adversarial Network (MACGAN) is proposed to improve scene visibility for optimal ground, aerial, and marine navigation, using the same set of parameters across all domains. The MACGAN is a lightweight network with four encoder and decoder blocks and multiple attention blocks in between, which enhances the image restoration process by focusing on the most important features. To evaluate the effectiveness of MACGAN, extensive qualitative and quantitative comparisons are conducted with state-of-the-art image-to-image translation models, all-in-one adverse weather removal models, and single-effect removal models. The results highlight the superior performance of MACGAN in terms of scene visibility improvement and restoration quality. Additionally, MACGAN is tested on real-world unseen image domains, including smog, dust, fog, rain, snow, and lightning, further validating its generalizability and robustness. Furthermore, an ablation study is conducted to analyze the contributions of the discriminator and attention blocks within the MACGAN architecture. The results confirm that both components play significant roles in the effectiveness of MACGAN, with the discriminator ensuring adversarial training and the attention blocks effectively capturing and enhancing important image features.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="http://creativecommons.org/licenses/by/4.0" target="_blank">http://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3289591" target="_blank">https://dx.doi.org/10.1109/access.2023.3289591</a></p>2023-06-26T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2023.3289591https://figshare.com/articles/journal_contribution/MACGAN_An_All-in-One_Image_Restoration_Under_Adverse_Conditions_Using_Multidomain_Attention-Based_Conditional_GAN/25205192CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/252051922023-06-26T06:00:00Z
spellingShingle MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
Maria Siddiqua (17949149)
Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Snow
Feature extraction
Rain
Image restoration
Image color analysis
Degradation
Clouds
Weather forecasting
Generative adversarial networks
Restoration
multidomain
adverse weather
navigation
aerial
marine
attention mechanism
status_str publishedVersion
title MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
title_full MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
title_fullStr MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
title_full_unstemmed MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
title_short MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
title_sort MACGAN: An All-in-One Image Restoration Under Adverse Conditions Using Multidomain Attention-Based Conditional GAN
topic Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Snow
Feature extraction
Rain
Image restoration
Image color analysis
Degradation
Clouds
Weather forecasting
Generative adversarial networks
Restoration
multidomain
adverse weather
navigation
aerial
marine
attention mechanism