Enabling Safe UAV Navigation in Transparent and Specular Environments via Generative Depth Completion | 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 Article Enabling Safe UAV Navigation in Transparent and Specular Environments via Generative Depth Completion Boyu Zhou, Pengcheng Zhu, Xulin Xiao, Hao Hu, Wei Pan, Huaxu Li, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9290835/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Reliable perception and autonomous navigation are critical capabilities for unmanned aerial vehicles (UAVs). Modern architecture is dominated by transparent and specular surfaces (TSS), yet these materials present a perceptual vacuum for conventional UAV sensing, leading to frequent collisions. In this work, we present a solution that enables UAVs to mimic the human ability to infer TSS geometry using only conventional sensors. We introduce a unified navigation framework centered on a geometry-guided diffusion-based depth completion model. By injecting sparse LiDAR measurements as explicit geometric constraints into the diffusion process, we resolve scale inconsistency and improve accuracy. To enable real-time performance, we utilize a single-step inference strategy derived from diffusion theory, bypassing iterative denoising to achieve high-speed depth generation on resource-constrained platforms. Furthermore, we introduce a cross-modal fusion mapping algorithm that fuses generative depth with LiDAR data, preventing the loss of critical obstacle cues. We validate our framework through extensive real-world flight experiments across diverse indoor, outdoor, and nighttime settings. Our approach outperforms state-of-the-art methods in depth completion and mapping, effectively bridging the TSS-blindness gap in robotics and extending the operational scope of autonomous UAVs in complex human-centric environments. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Engineering Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryVideo1.mp4 Supplementary Video 1 SupplementaryVideo2.mp4 Supplementary Video 2 SupplementaryVideo3.mp4 Supplementary Video 3 SupplementaryVideo4.mp4 Supplementary Video 4 SupplementaryVideo5.mp4 Supplementary Video 5 SupplementaryVideo6.mp4 Supplementary Video 6 Cite Share Download PDF Status: Under Review 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-9290835","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":622871418,"identity":"d720a0d8-8849-42e3-9ef1-a77b8512e163","order_by":0,"name":"Boyu Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYDACCQYGZgYGGwiHsQFIHCBOSxoDmCJFy2EStMjPbj4mXdh23t7g/PmDD37uYJDju5HA+LkAjxbGOcfSpGe23U7ccCOZ2bD3DIOx5I0EZukZeLQwS+SYSfO23U4wuMHMJs3YxgDUm8DGzINHCxtEyzmgww6z/wZqqSeohQei5QDjhgPJbMxALUDrCGiRkEhLtp5xLjlx5o1kY8neNgnDmWceNkvj0yI/I/ng7YIyO3u+8wcffvjZZiPPdzz54Gd8WsCAkQ1hKwM0dgiBP0SoGQWjYBSMgpELANF8SKqLxuhvAAAAAElFTkSuQmCC","orcid":"","institution":"Southern University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Boyu","middleName":"","lastName":"Zhou","suffix":""},{"id":622871419,"identity":"0739d9c2-f05b-4112-b257-f0d0a790bc7f","order_by":1,"name":"Pengcheng Zhu","email":"","orcid":"","institution":"Southern University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Pengcheng","middleName":"","lastName":"Zhu","suffix":""},{"id":622871420,"identity":"f2b72eea-c7aa-4d9c-a344-7906d5781cdb","order_by":2,"name":"Xulin Xiao","email":"","orcid":"https://orcid.org/0009-0001-0462-4326","institution":"The Hong Kong University of Science and Technology (Guangzhou)","correspondingAuthor":false,"prefix":"","firstName":"Xulin","middleName":"","lastName":"Xiao","suffix":""},{"id":622871421,"identity":"d611888b-2635-4ca2-aa76-7e3bf86313cc","order_by":3,"name":"Hao Hu","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Hu","suffix":""},{"id":622871422,"identity":"f56fe420-7550-49f4-929d-7c271be1ef74","order_by":4,"name":"Wei Pan","email":"","orcid":"","institution":"Southern University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Pan","suffix":""},{"id":622871423,"identity":"b31f6954-6a86-4d98-8d3c-b17c68a3f39c","order_by":5,"name":"Huaxu Li","email":"","orcid":"https://orcid.org/0009-0006-3602-9034","institution":"Southern University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Huaxu","middleName":"","lastName":"Li","suffix":""},{"id":622871424,"identity":"70ff8d24-23bf-4fcb-97a9-54087753d6ec","order_by":6,"name":"Qingkai Yang","email":"","orcid":"https://orcid.org/0000-0001-9247-7786","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Qingkai","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2026-04-01 11:00:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9290835/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9290835/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106964296,"identity":"cc64d2bd-7054-4461-9b77-7ba5d71e2447","added_by":"auto","created_at":"2026-04-15 09:49:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2621573,"visible":true,"origin":"","legend":"Article File","description":"","filename":"EnablingSafeUAVNavigationinTransparentandSpecularEnvironmentsviaGenerativeDepthCompletion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1_covered_d43ef84e-d8bc-43f5-b8ae-8c24c7358e7a.pdf"},{"id":106936997,"identity":"d8a0f666-f56f-4e56-a002-7894760d6ed6","added_by":"auto","created_at":"2026-04-15 03:41:26","extension":"mp4","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":330570252,"visible":true,"origin":"","legend":"Supplementary Video 1","description":"","filename":"SupplementaryVideo1.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1/3422e557ff56f5daae53afe1.mp4"},{"id":106936998,"identity":"a10c532b-97b8-49cd-ab3a-842268ed2900","added_by":"auto","created_at":"2026-04-15 03:41:26","extension":"mp4","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":70356529,"visible":true,"origin":"","legend":"Supplementary Video 2","description":"","filename":"SupplementaryVideo2.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1/274812756f770e5f12dfe891.mp4"},{"id":106936999,"identity":"416475f6-1237-402f-a8d6-d50a44feacd8","added_by":"auto","created_at":"2026-04-15 03:41:26","extension":"mp4","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":87325692,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Video 3\u003c/p\u003e","description":"","filename":"SupplementaryVideo3.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1/490c33fdf149f6ce1e394b6c.mp4"},{"id":106937000,"identity":"e8c2b7ba-ad5b-488f-801e-59c1376ddda4","added_by":"auto","created_at":"2026-04-15 03:41:26","extension":"mp4","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":73022873,"visible":true,"origin":"","legend":"Supplementary Video 4","description":"","filename":"SupplementaryVideo4.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1/78705e30d9e5e2f8c778552e.mp4"},{"id":106960986,"identity":"9cbd738d-f93d-4e54-aee0-cce57cb1cc17","added_by":"auto","created_at":"2026-04-15 09:23:53","extension":"mp4","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":88162430,"visible":true,"origin":"","legend":"Supplementary Video 5","description":"","filename":"SupplementaryVideo5.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1/9ceff8610384013be4c2ff85.mp4"},{"id":106937002,"identity":"7faab58d-13b5-492a-994a-6fba63605024","added_by":"auto","created_at":"2026-04-15 03:41:26","extension":"mp4","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":16870285,"visible":true,"origin":"","legend":"Supplementary Video 6","description":"","filename":"SupplementaryVideo6.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9290835/v1/0589c28dcfdcef7595a320e1.mp4"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Enabling Safe UAV Navigation in Transparent and Specular Environments via Generative Depth Completion","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9290835/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9290835/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Reliable perception and autonomous navigation are critical capabilities for unmanned aerial vehicles (UAVs). Modern architecture is dominated by transparent and specular surfaces (TSS), yet these materials present a perceptual vacuum for conventional UAV sensing, leading to frequent collisions. In this work, we present a solution that enables UAVs to mimic the human ability to infer TSS geometry using only conventional sensors. We introduce a unified navigation framework centered on a geometry-guided diffusion-based depth completion model. By injecting sparse LiDAR measurements as explicit geometric constraints into the diffusion process, we resolve scale inconsistency and improve accuracy. To enable real-time performance, we utilize a single-step inference strategy derived from diffusion theory, bypassing iterative denoising to achieve high-speed depth generation on resource-constrained platforms. Furthermore, we introduce a cross-modal fusion mapping algorithm that fuses generative depth with LiDAR data, preventing the loss of critical obstacle cues. We validate our framework through extensive real-world flight experiments across diverse indoor, outdoor, and nighttime settings. Our approach outperforms state-of-the-art methods in depth completion and mapping, effectively bridging the TSS-blindness gap in robotics and extending the operational scope of autonomous UAVs in complex human-centric environments.","manuscriptTitle":"Enabling Safe UAV Navigation in Transparent and Specular Environments via Generative Depth Completion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-15 03:40:58","doi":"10.21203/rs.3.rs-9290835/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f43d2fc8-a7ae-4a6d-8ba4-6ee4b8c6a543","owner":[],"postedDate":"April 15th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"This content is not available.","date":"2026-05-03T21:23:00+00:00","index":1,"fulltext":"This content is not available."}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66283129,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":66283130,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2026-04-15T03:40:58+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-15 03:40:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9290835","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9290835","identity":"rs-9290835","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.