TriORU2-Net++: Attention-Guided Three-StageU2-Net++ for Light Field Occlusion Removal

TriORU2-Net++: Attention-Guided Three-StageU2-Net++ for Light Field Occlusion Removal | 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 TriORU 2 -Net++: Attention-Guided Three-StageU 2 -Net++ for Light Field Occlusion Removal Mostafa Farouk Senussi, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7599592/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract We introduce TriORU2-Net++, a novel three-stage architecture designed to address the persistent challenge of occlusion removal in light-field (LF) images by leveraging adaptive attention-guided feature integration and progressive hierarchical reconstruction. Unlike existing methods that struggle to fully exploit spatial hierarchies and adaptively restore occluded regions across scales, our model incorporates a ResASPP-AttFPN feature extractor, which integrates Residual Atrous Spatial Pyramid Pooling (ResASPP) with a spatial attention-enhanced Feature Pyramid Network (AttFPN) to selectively fuse multiscale features while emphasizing salient spatial cues essential for occlusion localization. The core of our framework is a tri-stage U2-Net++ reconstruction module, which performs progressive restoration through three hierarchically connected encoder-decoder stages of decreasing depth (4-level, 3-level, and 2-level), each built on VGG-based blocks and dense skip connections to recover increasingly refined background content. To further enhance detail preservation and structural consistency, we introduce a residual feature refiner (RFR) that consolidates residual cues and sharpens the boundaries of objects. Extensive experiments show that our method outperforms state-of-the-art (SOTA) approaches in both quantitative metrics and visual quality. Light Field Imaging Occlusion Removal Tri-Stage U2-Net++ Residual ASPP (ResASPP) Attention-Guided FPN (AttFPN) Residual Feature Refiner (RFR) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 28 Feb, 2026 Reviews received at journal 28 Feb, 2026 Reviews received at journal 06 Feb, 2026 Reviewers agreed at journal 21 Jan, 2026 Reviews received at journal 21 Jan, 2026 Reviewers agreed at journal 20 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviewers invited by journal 14 Jan, 2026 Editor assigned by journal 09 Nov, 2025 Submission checks completed at journal 13 Sep, 2025 First submitted to journal 12 Sep, 2025 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-7599592","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":575707737,"identity":"b0c4b907-c859-4844-b0e3-15fdb326ca52","order_by":0,"name":"Mostafa Farouk Senussi","email":"","orcid":"","institution":"Chungbuk National University","correspondingAuthor":false,"prefix":"","firstName":"Mostafa","middleName":"Farouk","lastName":"Senussi","suffix":""},{"id":575707738,"identity":"54bac0ea-0cf0-4bc7-b9b3-0cd5866ac412","order_by":1,"name":"Mahmoud Abdalla","email":"","orcid":"","institution":"Chungbuk National University","correspondingAuthor":false,"prefix":"","firstName":"Mahmoud","middleName":"","lastName":"Abdalla","suffix":""},{"id":575707740,"identity":"6478c7a0-7a7b-44c4-a56c-1ad7bb425e54","order_by":2,"name":"Mahmoud SalahEldin Kasem","email":"","orcid":"","institution":"Chungbuk National University","correspondingAuthor":false,"prefix":"","firstName":"Mahmoud","middleName":"SalahEldin","lastName":"Kasem","suffix":""},{"id":575707744,"identity":"614db654-ff2e-4c51-a88f-92510720d02e","order_by":3,"name":"Mohamed Mahmoud","email":"","orcid":"","institution":"Chungbuk National University","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Mahmoud","suffix":""},{"id":575707746,"identity":"491489c1-a4e9-4938-9683-383c90630059","order_by":4,"name":"Hyun-Soo Kang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxElEQVRIiWNgGAWjYBACAwY2EGUDZMAEiNSSRrqWwyRoMec/lvi54Nd5eXPpHgOGHzUMxuYNBLRYzkg7LD2z77bhzjlnDBh7jjGYyRwg5LAb7A3SvD23Ewxu5Bgw8DYw2EgQ9Mv5482/eXvOgbUw/iVKy4G0Y9I8Pw6AtTADbTEjrOVGWpo1b0Oy4c4ZaQWHZY5JGBPhsGPGt3n+2MmbSyRvfPimxsZwBiEtYMDYBqEPMDAQtAMG/hCrcBSMglEwCkYkAAAXITxOuI8tsgAAAABJRU5ErkJggg==","orcid":"","institution":"Chungbuk National University","correspondingAuthor":true,"prefix":"","firstName":"Hyun-Soo","middleName":"","lastName":"Kang","suffix":""}],"badges":[],"createdAt":"2025-09-12 11:38:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7599592/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7599592/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100549190,"identity":"30a1bf6b-a2e9-4179-ac55-89875154678e","added_by":"auto","created_at":"2026-01-19 08:22:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4652392,"visible":true,"origin":"","legend":"","description":"","filename":"TriORU2Net.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7599592/v1_covered_b81d5320-2323-4c60-86f9-1c1273164ce8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eTriORU\u003csup\u003e2\u003c/sup\u003e-Net++: Attention-Guided Three-StageU\u003csup\u003e2\u003c/sup\u003e-Net++ for Light Field Occlusion Removal\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"journal-of-big-data","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bigd","sideBox":"Learn more about [Journal of Big Data](http://journalofbigdata.springeropen.com)","snPcode":"40537","submissionUrl":"https://submission.nature.com/new-submission/40537/3","title":"Journal of Big Data","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Light Field Imaging, Occlusion Removal, Tri-Stage U2-Net++, Residual ASPP (ResASPP), Attention-Guided FPN (AttFPN), Residual Feature Refiner (RFR)","lastPublishedDoi":"10.21203/rs.3.rs-7599592/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7599592/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We introduce TriORU2-Net++, a novel three-stage architecture designed to address the persistent challenge of occlusion removal in light-field (LF) images by leveraging adaptive attention-guided feature integration and progressive hierarchical reconstruction. Unlike existing methods that struggle to fully exploit spatial hierarchies and adaptively restore occluded regions across scales, our model incorporates a ResASPP-AttFPN feature extractor, which integrates Residual Atrous Spatial Pyramid Pooling (ResASPP) with a spatial attention-enhanced Feature Pyramid Network (AttFPN) to selectively fuse multiscale features while emphasizing salient spatial cues essential for occlusion localization. The core of our framework is a tri-stage U2-Net++ reconstruction module, which performs progressive restoration through three hierarchically connected encoder-decoder stages of decreasing depth (4-level, 3-level, and 2-level), each built on VGG-based blocks and dense skip connections to recover increasingly refined background content. To further enhance detail preservation and structural consistency, we introduce a residual feature refiner (RFR) that consolidates residual cues and sharpens the boundaries of objects. Extensive experiments show that our method outperforms state-of-the-art (SOTA) approaches in both quantitative metrics and visual quality.","manuscriptTitle":"TriORU2-Net++: Attention-Guided Three-StageU2-Net++ for Light Field Occlusion Removal","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-19 04:10:38","doi":"10.21203/rs.3.rs-7599592/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-28T08:38:19+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-28T07:13:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-06T09:30:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"53563080270229951719547266940428176321","date":"2026-01-21T19:33:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-21T13:49:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310475197905742221505162708340238977957","date":"2026-01-20T20:03:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"22793707194479322004275196452295069940","date":"2026-01-14T13:01:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"108349836684400870756585683715655394626","date":"2026-01-14T12:59:30+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-14T12:43:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-09T20:49:59+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-13T07:14:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Big Data","date":"2025-09-12T10:02:55+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-big-data","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bigd","sideBox":"Learn more about [Journal of Big Data](http://journalofbigdata.springeropen.com)","snPcode":"40537","submissionUrl":"https://submission.nature.com/new-submission/40537/3","title":"Journal of Big Data","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"875172b7-59cc-4f99-ba93-3e4f9ade2808","owner":[],"postedDate":"January 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-02T22:38:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-19 04:10:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7599592","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7599592","identity":"rs-7599592","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}