Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow Removal

Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow 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 Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow Removal Xiaofeng Zhang, Zishan Xu, Hao Tang, Chaochen Gu, Shanying Zhu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4194150/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Segment Anything Model (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguishing between shadows and their backgrounds. To address this, we proposed ShadClips, which consists of SAM-optimizer and SONet. It has dramatically enhanced SAM’s ability to segment shadow images, differentiating between the background and both soft and hard shadows adeptly. Due to its dependence on pixel point inputs, the SAM-Optimizer interface could do better. This method presents challenges, especially when dealing with long, extended shadows. To make the user experience more intuitive and effective, we incorporated the capabilities of CLIPs. Therefore, simple text descriptions like “A photo of a shadow” can be used to guide the SAM-Optimizer, allowing it to select the most relevant shadow mask from SAM’s comprehensive category list. Meanwhile, we introduce SONet to shadow removal. A large number of experiments on ISTD/SRD prove that the proposed method is effective and satisfactory. The source code of the ShadClips can be accessed from https://github.com/zhangbaijin/SAM-helps-Shadow . CLIP Shadow Removal Segment Anything Model SONet 1 Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-4194150","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":287250724,"identity":"e03b2991-423b-4633-8a6d-fccc63d09bfa","order_by":0,"name":"Xiaofeng Zhang","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Xiaofeng","middleName":"","lastName":"Zhang","suffix":""},{"id":287250725,"identity":"3867c042-11dc-4f5f-b700-bd8c9dfa18b5","order_by":1,"name":"Zishan Xu","email":"","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zishan","middleName":"","lastName":"Xu","suffix":""},{"id":287250726,"identity":"4060b1c0-f809-4388-acf2-139027333fc9","order_by":2,"name":"Hao Tang","email":"","orcid":"","institution":"Carnegie Mellon University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Tang","suffix":""},{"id":287250727,"identity":"a192ef7f-50e1-4622-9c2b-2652a21c39d1","order_by":3,"name":"Chaochen Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYBACxgYwZQNlsBGvJY2BsY1YLVBwGKqaGC3M7YefSX5tO2/PPL/HgOFD2WEG/tkNBBzWk2YmLdt2O7GxjceAcca5wwwSdw4Q0NKQwyYt2XY7gRGohZm37TCDgUQCAS39b0BaztmDtfwlSsuMHDbJj20HGEEOY2YkTsszY2uGc8lAv6QVHOw5l84jcYOAFsP+5Ic3f5TZ2Rs2H9744EeZtRz/DEJaGhhYpHkgDIYDQJoHv3ogkAdGzccfEMYoGAWjYBSMAuwAAHQZQOoDWrHEAAAAAElFTkSuQmCC","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":true,"prefix":"","firstName":"Chaochen","middleName":"","lastName":"Gu","suffix":""},{"id":287250728,"identity":"e89bbc5a-3a39-4378-98d4-bc98cfa36e4e","order_by":4,"name":"Shanying Zhu","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Shanying","middleName":"","lastName":"Zhu","suffix":""},{"id":287250729,"identity":"fcb78981-30f9-4b14-9265-d468e1a3acc7","order_by":5,"name":"Xinping Guan","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Xinping","middleName":"","lastName":"Guan","suffix":""}],"badges":[],"createdAt":"2024-03-31 04:14:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4194150/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4194150/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60938822,"identity":"113e49f2-a1ee-4e57-aaa7-c12eaaba2bf5","added_by":"auto","created_at":"2024-07-23 20:11:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9562814,"visible":true,"origin":"","legend":"","description":"","filename":"TVCshadow.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4194150/v1_covered_46613fab-19be-4dd5-a7bc-23dbb2a3e6a1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow Removal","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"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":"CLIP, Shadow Removal, Segment Anything Model, SONet 1","lastPublishedDoi":"10.21203/rs.3.rs-4194150/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4194150/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Segment Anything Model (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguishing between shadows and their backgrounds. To address this, we proposed ShadClips, which consists of SAM-optimizer and SONet. It has dramatically enhanced SAM’s ability to segment shadow images, differentiating between the background and both soft and hard shadows adeptly. Due to its dependence on pixel point inputs, the SAM-Optimizer interface could do better. This method presents challenges, especially when dealing with long, extended shadows. To make the user experience more intuitive and effective, we incorporated the capabilities of CLIPs. Therefore, simple text descriptions like “A photo of a shadow” can be used to guide the SAM-Optimizer, allowing it to select the most relevant shadow mask from SAM’s comprehensive category list. Meanwhile, we introduce SONet to shadow removal. A large number of experiments on ISTD/SRD prove that the proposed method is effective and satisfactory. The source code of the ShadClips can be accessed from https://github.com/zhangbaijin/SAM-helps-Shadow.","manuscriptTitle":"Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow Removal","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-04 07:05:03","doi":"10.21203/rs.3.rs-4194150/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":"73fc70e2-a6e6-41b3-a21b-d2bb616b4188","owner":[],"postedDate":"April 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-07-23T20:03:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-04 07:05:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4194150","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4194150","identity":"rs-4194150","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}