Challenges of Depth Estimation for Transparent Objects

Challenges of Depth Estimation for Transparent Objects | 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 Challenges of Depth Estimation for Transparent Objects Jean-Baptiste Weibel, Stefan Thalhammer, Markus Vincze This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4270684/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 Transparent objects and surfaces are pervasive in man-made environments and need to be considered in any vision system. Accurate depth data is a key factor for the reliability of such systems, requiring methods tailored for transparency to overcome the sensing shortcomings. However, the current state-of-the-art methods to predict the depth of such objects are not yet reliable enough to ensure safe operation of autonomous systems in arbitrary complex environments. In order to better understand and improve upon existing solutions, we evaluate the performance of a variety of depth estimation methods. Doing so, we disentangle the different factors impacting their performance. Among our findings, neural radiance fields offer the best accuracy, but are very sensitive to the number of images used to understand the scene, and do not benefit from any level of object understanding to help them fill in the gaps. Transparent object perception Depth Estimation Depth Completion 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-4270684","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":291957613,"identity":"5b0ef6b8-7414-4527-a040-ea4d1bf281f6","order_by":0,"name":"Jean-Baptiste Weibel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIie3PsWqDQBzH8f9xkOkaV+UCfYW/S6GQxFdRhMydglBoAoVzEbI65CHyCCc3uIhdBYeapXOyCQ2kB0KTDhcydrjvoid8/CmAzfYvIwLgZQpAhyO7k+BiIPKKuDfMSBM13Mqrx0aC5bvoDvjx6KQPkh6Fmjh8TQ49zN+MpCpSP8fWz9U4hEIo5m0l9TKIjStPTSQ4w5bsKENNWoZNCFz/mpl87gU/YR38kqAJ6TfA6sYKERxQRpcVNxzpFWUkQRWlfoZxnCuGsqrPzNWf+pxh6a0NxEvLr65P5rPNpvK7ZLkInDxWTZ+8OqaVP8nhQvT78S5gs9lsNkM/ixpS85z6fpIAAAAASUVORK5CYII=","orcid":"","institution":"TU Wien","correspondingAuthor":true,"prefix":"","firstName":"Jean-Baptiste","middleName":"","lastName":"Weibel","suffix":""},{"id":291957614,"identity":"c01c0392-c067-4d09-8871-12cd33f30f98","order_by":1,"name":"Stefan Thalhammer","email":"","orcid":"","institution":"UAS Technikum","correspondingAuthor":false,"prefix":"","firstName":"Stefan","middleName":"","lastName":"Thalhammer","suffix":""},{"id":291957615,"identity":"cb1492fe-9142-4a6a-b3f3-2dddf6ff91f7","order_by":2,"name":"Markus Vincze","email":"","orcid":"","institution":"TU Wien","correspondingAuthor":false,"prefix":"","firstName":"Markus","middleName":"","lastName":"Vincze","suffix":""}],"badges":[],"createdAt":"2024-04-15 15:27:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4270684/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4270684/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":69555096,"identity":"f6ed5c82-1b10-4971-bb12-91111086d29b","added_by":"auto","created_at":"2024-11-21 15:16:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":846645,"visible":true,"origin":"","legend":"","description":"","filename":"MVAJournalChallengesofDepthEstimationforTransparentObjects.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4270684/v1_covered_e410d4e0-e227-4aa1-bb53-adfe0c86e2a6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Challenges of Depth Estimation for Transparent Objects","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":"Transparent object perception, Depth Estimation, Depth Completion","lastPublishedDoi":"10.21203/rs.3.rs-4270684/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4270684/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Transparent objects and surfaces are pervasive in man-made environments and need to be considered in any vision system.\nAccurate depth data is a key factor for the reliability of such systems, requiring methods tailored for transparency to overcome the sensing shortcomings.\nHowever, the current state-of-the-art methods to predict the depth of such objects are not yet reliable enough to ensure safe operation of autonomous systems in arbitrary complex environments.\nIn order to better understand and improve upon existing solutions, we evaluate the performance of a variety of depth estimation methods.\nDoing so, we disentangle the different factors impacting their performance. \nAmong our findings, neural radiance fields offer the best accuracy, but are very sensitive to the number of images used to understand the scene, and do not benefit from any level of object understanding to help them fill in the gaps.\n","manuscriptTitle":"Challenges of Depth Estimation for Transparent Objects","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-22 15:08:07","doi":"10.21203/rs.3.rs-4270684/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":"3651268a-24de-47d7-b23d-9ba6c32fecb1","owner":[],"postedDate":"April 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-11-21T15:08:38+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-22 15:08:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4270684","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4270684","identity":"rs-4270684","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}