CrackLite: Lightweight Topology-Aware Crack Segmentation via Direction-Guided Topology Aggregation

CrackLite: Lightweight Topology-Aware Crack Segmentation via Direction-Guided Topology Aggregation | 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 CrackLite: Lightweight Topology-Aware Crack Segmentation via Direction-Guided Topology Aggregation Longsheng Bao, Si Chen, Yuyang Bao, Baoxian Li, Jiakang Zhao, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9352500/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Concrete crack segmentation in field imagery remains challenging because cracks are thin, elongated, low-contrast, and easily confused with stains, shadows, and heterogeneous textures. Existing lightweight networks reduce computation but often fragment long crack paths and blur fine boundaries. We present CrackLite, a lightweight topology-aware network for high-resolution concrete crack segmentation. CrackLite retains a hierarchical encoder–decoder backbone and introduces Direction-Guided Topology Aggregation (DGTA), which estimates local orientation priors and aggregates context along candidate crack directions through confidence-gated fusion. To improve thin-structure delineation, a Normal-Calibrated Local Geometry Refinement (NLGR) module sharpens crack boundaries and suppresses texture-induced false responses, while a training-only auxiliary branch regularizes centerline continuity and boundary localization without increasing inference-time cost. Experiments on a self-collected bridge crack dataset and two public benchmarks show that CrackLite achieves a favorable accuracy–efficiency trade-off for morphology-preserving concrete crack segmentation. Crack segmentation Topology-aware segmentation Direction-guided context aggregation Thin-structure modeling Lightweight architecture Concrete surface inspection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 19 Apr, 2026 Reviewers invited by journal 13 Apr, 2026 Editor assigned by journal 10 Apr, 2026 Submission checks completed at journal 10 Apr, 2026 First submitted to journal 08 Apr, 2026 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-9352500","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":625897192,"identity":"a5fe3e0d-4aeb-4f00-b018-082072685fcc","order_by":0,"name":"Longsheng Bao","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Longsheng","middleName":"","lastName":"Bao","suffix":""},{"id":625897193,"identity":"978c3683-8dd8-4f8b-b00e-105a6ae2aa6b","order_by":1,"name":"Si Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIiWNgGAWjYDACZgaGAwwGDCDE+ADIl2FgYCNeCzOI4iGsBQaAytkkiNIi387+8OCPAgZ5c/beYxUf2/7w8LO3JTD8qNiG2/DDPCDEYLiz51zazZltBjySPccOMPacuY1bCzMPw2GgqxIMbuSY3eYFajG4kd7AzNiGW4t8M/uDgz9AWu6/MSsmSgvIigM8YFt4zJghWtIO4NUC9YuE4YYzOcaSM84Zg/yScBCfX+T7jz/++OOPjbzB8TOGHz6UyckBQ8zwwY8KPA6DAAlU7gFC6kfBKBgFo2AU4AcAN1ZQCLscG6QAAAAASUVORK5CYII=","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":true,"prefix":"","firstName":"Si","middleName":"","lastName":"Chen","suffix":""},{"id":625897194,"identity":"f53abb2b-be7e-487f-bd53-f488d79d1dbf","order_by":2,"name":"Yuyang Bao","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Yuyang","middleName":"","lastName":"Bao","suffix":""},{"id":625897195,"identity":"8595a2e3-41ac-45f4-8b67-5ac694a52b36","order_by":3,"name":"Baoxian Li","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Baoxian","middleName":"","lastName":"Li","suffix":""},{"id":625897196,"identity":"a011ec9a-f139-454f-bb16-2e2450362ab2","order_by":4,"name":"Jiakang Zhao","email":"","orcid":"","institution":"Inner Mongolia University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiakang","middleName":"","lastName":"Zhao","suffix":""},{"id":625897197,"identity":"580cb47d-03ae-4c05-bd06-31c9d7b55be2","order_by":5,"name":"Ling Yu","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Ling","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2026-04-08 06:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9352500/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9352500/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107487961,"identity":"5f3c7b0d-629c-4158-9351-f64647180a20","added_by":"auto","created_at":"2026-04-22 02:43:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":941231,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript0409.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9352500/v1_covered_47563ec9-92fb-42a6-a2d2-c27db5c231e8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CrackLite: Lightweight Topology-Aware Crack Segmentation via Direction-Guided Topology Aggregation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Crack segmentation, Topology-aware segmentation, Direction-guided context aggregation, Thin-structure modeling, Lightweight architecture, Concrete surface inspection","lastPublishedDoi":"10.21203/rs.3.rs-9352500/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9352500/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eConcrete crack segmentation in field imagery remains challenging because cracks are thin, elongated, low-contrast, and easily confused with stains, shadows, and heterogeneous textures. Existing lightweight networks reduce computation but often fragment long crack paths and blur fine boundaries. We present CrackLite, a lightweight topology-aware network for high-resolution concrete crack segmentation. CrackLite retains a hierarchical encoder\u0026ndash;decoder backbone and introduces Direction-Guided Topology Aggregation (DGTA), which estimates local orientation priors and aggregates context along candidate crack directions through confidence-gated fusion. To improve thin-structure delineation, a Normal-Calibrated Local Geometry Refinement (NLGR) module sharpens crack boundaries and suppresses texture-induced false responses, while a training-only auxiliary branch regularizes centerline continuity and boundary localization without increasing inference-time cost. Experiments on a self-collected bridge crack dataset and two public benchmarks show that CrackLite achieves a favorable accuracy\u0026ndash;efficiency trade-off for morphology-preserving concrete crack segmentation.\u003c/p\u003e","manuscriptTitle":"CrackLite: Lightweight Topology-Aware Crack Segmentation via Direction-Guided Topology Aggregation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 10:18:53","doi":"10.21203/rs.3.rs-9352500/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"307267722396428606681994986008395566359","date":"2026-04-20T01:49:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-13T19:14:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-10T09:32:36+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-10T09:32:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2026-04-08T06:23:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6d5ab086-0de3-4d13-829d-332610ca54a6","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-21T10:18:53+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 10:18:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9352500","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9352500","identity":"rs-9352500","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}