DC-GAN with Feature Attention for Single Image Dehazing

DC-GAN with Feature Attention for Single Image Dehazing | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article DC-GAN with Feature Attention for Single Image Dehazing TEWODROS MEGABIAW TASSEW, Nie Xuan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2717815/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Dec, 2023 Read the published version in Signal, Image and Video Processing → Version 1 posted You are reading this latest preprint version Abstract In recent years, the frequent occurrence of smog weather has affected people's health and has also had a major impact on computer vision application systems. Images captured in hazy environments suffer from quality degradation and other issues such as color distortion, low contrast, and lack of detail. This study proposes an end-to-end, adversarial neural network-based dehazing technique called DC-GAN that combines Dense and Residual blocks efficiently for improved dehazing performance. In addition, it also consists of channel attention and pixel attention, which can offer more versatility when dealing with different forms of data. The Wasserstein Generative Adversarial Network with Gradient Penality(WGAN-GP) was used as an enhancement method to correct the shortcomings in the original GAN's cost function and create an improvised loss. On the basis of the experiment results, the algorithm used in this paper is able to generate sharp images with high image quality. The processed images were simultaneously analyzed using the objective evaluation metrics Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). The findings demonstrate that the dehazing effect is favorable compared to other state-of-the-art dehazing algorithms, achieving a PSNR and SSIM of 14.7 and 0.54 for the indoor images, and 16.54 and 0.54 for the outdoor images respectively using the NTIRE 2018 dataset. Using the SOTS dataset, the model achieved a PSNR and SSIM of 23.98 and 0.87 for the indoor images, and 19.88 and 0.83 for the outdoor images. Image Dehazing Deep Learning Generative Adversarial Networks Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Full Text Additional Declarations Competing interests: The authors declare no competing interests. Cite Share Download PDF Status: Published Journal Publication published 22 Dec, 2023 Read the published version in Signal, Image and Video Processing → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-2717815","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":186081446,"identity":"bde3f619-f539-4c5c-9339-8981f3fb823b","order_by":0,"name":"TEWODROS MEGABIAW TASSEW","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABJUlEQVRIie2QMUvDQBTHXw1clwdZT5LqV4gEWodivoqhcNOFFlyKxBAI1EU6K/gh4uJ8cJAuAdeCSyCQqZtQt+rFakVI1FHwfhzHe4//j3ccgEbzN3HqC00z9gsAan+MO3FLHt8Ve/9alKqi+Gtl6Ai/otvBD4rXTdK95fQCQUh2vgyPEayrfokw7KXCqIqmLZhNDJ4vsJPM2CPP1MPsfOAiMDcVZOA0KZQ7RjDL0IBcKUQpNLi3EKSfCiS0STlcKWWTIYHx+oxvdspLu0JRKXGICKdMrdspol3J2UTyTCClYmQFc6pi4+ejW2fk3kjSb1K6l/Ku5GHkeQ+x/8TX0YFJGStW05PefJFUTUqNAJCfHXk79VcZLfkt0ZeOfJvVaDSaf8crseJbfZPKUWIAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-7951-4068","institution":"Northwestern Polytechnical University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"TEWODROS","middleName":"MEGABIAW","lastName":"TASSEW","suffix":""},{"id":186081447,"identity":"e5640f54-9785-4eb0-8b13-fe8b925aa907","order_by":1,"name":"Nie Xuan","email":"","orcid":"","institution":"Northwestern Polytechnical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Nie","middleName":"","lastName":"Xuan","suffix":""}],"badges":[],"createdAt":"2023-03-21 09:50:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2717815/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2717815/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-023-02877-5","type":"published","date":"2023-12-22T20:15:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":34922611,"identity":"83da7813-8ec5-4afb-a614-f13c603765c6","added_by":"auto","created_at":"2023-03-28 13:59:42","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":101002,"visible":true,"origin":"","legend":"Atmospheric scattering model","description":"","filename":"OnlineASM.png","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1/18f82392a4ece4596e0f4384.png"},{"id":34922633,"identity":"fc157a58-b6fa-4561-a840-b1282d89b671","added_by":"auto","created_at":"2023-03-28 13:59:45","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":606375,"visible":true,"origin":"","legend":"(a) and (e) are sample indoor hazy and ground truth images while (b) and (f) are sample outdoor hazy and ground truth images of the NTIRE 2018 dataset respectively, and (c) and (g) are sample indoor hazy and ground truth images while (d) and (h) are sample outdoor hazy and ground truth images of the RESIDE SOTS dataset respectively.","description":"","filename":"OnlineSampleimages.png","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1/6063156254a10bdf11d11e07.png"},{"id":34922613,"identity":"f47e0af5-7fc6-4600-a7a9-7bca25d4f3a7","added_by":"auto","created_at":"2023-03-28 13:59:43","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":204024,"visible":true,"origin":"","legend":"Network Architecture","description":"","filename":"OnlineGAN.png","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1/ae41305e153729ac2507cffd.png"},{"id":34922632,"identity":"0900f062-59db-4b28-b35c-dea5eddf39f5","added_by":"auto","created_at":"2023-03-28 13:59:44","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":352746,"visible":true,"origin":"","legend":"Building Blocks Explanation","description":"","filename":"Onlineexplanation.png","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1/1f1aff83069c94bada0b9416.png"},{"id":34924320,"identity":"7b23a489-15c6-4ef3-b3a3-528c8b70c164","added_by":"auto","created_at":"2023-03-28 14:07:45","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":77448,"visible":true,"origin":"","legend":"Discriminator","description":"","filename":"Onlinediscriminator.png","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1/dffb55b4159ea05df9cbc9a8.png"},{"id":34922612,"identity":"72298d42-f03e-4288-8640-f8edc50fbde9","added_by":"auto","created_at":"2023-03-28 13:59:42","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":831620,"visible":true,"origin":"","legend":"Qualitative results of DC-GAN on NTIRE 2018 and SOTS datasets. (a) and (b) represent indoor and outdoor images from NTIRE 2018 dataset, whereas (c) and (d) represent indoor and outdoor images from SOTS dataset respectively","description":"","filename":"OnlineDCGANimageresults.png","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1/d0194137ca71f24aef3cb275.png"},{"id":53032655,"identity":"5ddb7514-d720-46a2-820b-27d890c0c6de","added_by":"auto","created_at":"2024-03-19 20:16:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":945503,"visible":true,"origin":"","legend":"","description":"","filename":"DCGANSpringerLatex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2717815/v1_covered_0e6a9e45-91f1-47d0-b642-ac4fddb00589.pdf"}],"financialInterests":"\u003cp\u003eCompeting interests: The authors declare no competing interests.\u003c/p\u003e","formattedTitle":"DC-GAN with Feature Attention for Single Image Dehazing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Image Dehazing, Deep Learning, Generative Adversarial Networks","lastPublishedDoi":"10.21203/rs.3.rs-2717815/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2717815/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn recent years, the frequent occurrence of smog weather has affected people's health and has also had a major impact on computer vision application systems. Images captured in hazy environments suffer from quality degradation and other issues such as color distortion, low contrast, and lack of detail. This study proposes an end-to-end, adversarial neural network-based dehazing technique called DC-GAN that combines Dense and Residual blocks efficiently for improved dehazing performance. In addition, it also consists of channel attention and pixel attention, which can offer more versatility when dealing with different forms of data. The Wasserstein Generative Adversarial Network with Gradient Penality(WGAN-GP) was used as an enhancement method to correct the shortcomings in the original GAN's cost function and create an improvised loss. On the basis of the experiment results, the algorithm used in this paper is able to generate sharp images with high image quality. The processed images were simultaneously analyzed using the objective evaluation metrics Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). The findings demonstrate that the dehazing effect is favorable compared to other state-of-the-art dehazing algorithms, achieving a PSNR and SSIM of 14.7 and 0.54 for the indoor images, and 16.54 and 0.54 for the outdoor images respectively using the NTIRE 2018 dataset. Using the SOTS dataset, the model achieved a PSNR and SSIM of 23.98 and 0.87 for the indoor images, and 19.88 and 0.83 for the outdoor images. \u003c/p\u003e","manuscriptTitle":"DC-GAN with Feature Attention for Single Image Dehazing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-03-28 13:59:32","doi":"10.21203/rs.3.rs-2717815/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e727cd8e-da31-4c85-874d-a663b4f25f3d","owner":[],"postedDate":"March 28th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-03-19T20:15:52+00:00","versionOfRecord":{"articleIdentity":"rs-2717815","link":"https://doi.org/10.1007/s11760-023-02877-5","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2023-12-22 20:15:52","publishedOnDateReadable":"December 22nd, 2023"},"versionCreatedAt":"2023-03-28 13:59:32","video":"","vorDoi":"10.1007/s11760-023-02877-5","vorDoiUrl":"https://doi.org/10.1007/s11760-023-02877-5","workflowStages":[]},"version":"v1","identity":"rs-2717815","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2717815","identity":"rs-2717815","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}