CNN Models for Accurate Pose Localization

CNN Models for Accurate Pose Localization | 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Article CNN Models for Accurate Pose Localization Achref ELOUNI, eric royer, chateau thierry This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4283976/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 Visual Localization is the problem of estimating the camera pose of a given image relative to a visual representation of a known scene. The estimation process becomes increasingly difficult due to factors such as a large quantity of outliers and changes in viewpoints. To overcome these challenges, we leverage semantic segmentation algorithms to enhance the localization performance. We propose three distinct approaches that effectively combine semantic and visual information, allowing us to assign more than one label to each keypoint. We compare the performance of these methods against state-of-the-art techniques and evaluate the scenario where only mono labels are utilized. The evaluation is conducted on four datasets (Dubrovnik, Rome, Aachen, and Vienna). Through extensive experimentation, we demonstrate that by incorporating both visual and semantic information, the accuracy of pose estimation can be significantly improved in terms of both time efficiency and precision. Image Localization Pose Estimation Semantic Segmentation Image Retrieval SfM 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-4283976","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":292598275,"identity":"e4bfb2ef-c096-4e7c-bc8c-135b46aaad8e","order_by":0,"name":"Achref ELOUNI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIie3NsQrCMBCA4SuBdKl2jUvzCi0FHfRhTgRdxFEcBAtCXXyACuI7uHQuBOoSd8f6Bh07ONiog1NaN4f8cMctHwdgMv1lTj0jgK66caW2VbQgUwD6IlJt4v9ArLgFcXfXvCwRPGrv+8X9JLgbEVrqCJOLySFBCKkjB/44FUGSEZJo39yckHQqGMds3mc1QchcoRVckQfC5k2OAnn9RUt8RQAB6YtEAv0mEsh5aO2RBbGTLxnms+AsGoh3kSFUOOKuvU171XrIvctWTz6xr7sVMJlMJpO2J7tKPSv958XmAAAAAElFTkSuQmCC","orcid":"","institution":"Institut Pascal","correspondingAuthor":true,"prefix":"","firstName":"Achref","middleName":"","lastName":"ELOUNI","suffix":""},{"id":292598276,"identity":"71214f8c-b7b5-42ad-ba3c-7fdb8b5157f6","order_by":1,"name":"eric royer","email":"","orcid":"","institution":"Institut Pascal","correspondingAuthor":false,"prefix":"","firstName":"eric","middleName":"","lastName":"royer","suffix":""},{"id":292598278,"identity":"d53b6ffb-769b-4122-8a2a-96b2d0e466a7","order_by":2,"name":"chateau thierry","email":"","orcid":"","institution":"Institut Pascal","correspondingAuthor":false,"prefix":"","firstName":"chateau","middleName":"","lastName":"thierry","suffix":""}],"badges":[],"createdAt":"2024-04-17 21:02:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4283976/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4283976/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64627519,"identity":"960e165f-89eb-4b71-bb84-e824398f2cdf","added_by":"auto","created_at":"2024-09-16 18:37:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":648542,"visible":true,"origin":"","legend":"","description":"","filename":"doc.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4283976/v1_covered_b8f1fe8d-2c5d-4757-b1c2-5325a2f91daf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CNN Models for Accurate Pose Localization","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":"Image Localization, Pose Estimation, Semantic Segmentation, Image Retrieval, SfM","lastPublishedDoi":"10.21203/rs.3.rs-4283976/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4283976/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Visual Localization is the problem of estimating the camera pose of a given image relative to a visual representation of a known scene. The estimation process becomes increasingly difficult due to factors such as a large quantity of outliers and changes in viewpoints. To overcome these challenges, we leverage semantic segmentation algorithms to enhance the localization performance. We propose three distinct approaches that effectively combine semantic and visual information, allowing us to assign more than one label to each keypoint. We compare the performance of these methods against state-of-the-art techniques and evaluate the scenario where only mono labels are utilized. The evaluation is conducted on four datasets (Dubrovnik, Rome, Aachen, and Vienna). Through extensive experimentation, we demonstrate that by incorporating both visual and semantic information, the accuracy of pose estimation can be significantly improved in terms of both time efficiency and precision.","manuscriptTitle":"CNN Models for Accurate Pose Localization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-22 03:05:02","doi":"10.21203/rs.3.rs-4283976/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":"a49ba314-cae6-4bdb-a6fb-653887c4e1c5","owner":[],"postedDate":"April 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-09-16T18:29:24+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-22 03:05:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4283976","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4283976","identity":"rs-4283976","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}