[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85726-en":3,"doc-seo-85726-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85726,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","RASR Range Aware Scale Recovery for Metric UAV Navigation","Range-aware Scale Recovery (RASR) targets UAV last-meter navigation when GNSS is denied, where controllers require accurate metric distance and heading commands. PairUAV-style dense pair-geometry foundations transfer relative structure well but produce distance scales that remain poorly calibrated, leaving costly range-dependent residuals near the goal. RASR isolates a transferable scale-recovery core from a protocol-specific calibration module, with range-bucket residual correction and command-grid alignment fixed for inference. On the Multimedia 2026 PairUAV online evaluation, RASR achieves a total score of 0.003189.","RASR: Range-Aware Scale Recovery for Metric UAV Navigation  \nHongtao Liang 1 Xinyu Shao2,3 Chenxu Wang4 Yiyao Wan 1 Jiahuan Ji5 Fangwei Ye6 Fuhui Zhou5 Qihui Wu 1  \n1 College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, China  \n2 Shenzhen International Graduate School, Tsinghua University, China, 3Noah Ark Lab, Huawei, China  \n4 College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, China  \n5 College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, China  \n6 College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China  \nNanjing and Shenzhen, China  \narXiv :2607 .09815v1 [ cs .RO] 10 Jul 2026  \nAbstract  \nUnder Global Navigation Satellite System (GNSS) denial, a UAV controller still needs a distance and heading command it can execute, making accurate metric last-meter navigation essential. Dense pairgeometry foundation models transfer relative structure well, yet the distance scale of their raw metric outputs remains poorly calibrated. Under the relative error metric of PairUAV, correcting only the average scale can still leave costly, distance-dependent residuals near the goal. To address this scale mismatch, Range-Aware Scale Recovery (RASR) separates a transferable scale-recovery core from a protocol-specific calibration module in a per-pair system fixed at inference. The core compresses frozen Matching And Stereo 3D Reconstruction (MASt3R)-style geometry into a compact descriptor and uses global calibration to recover the dominant metric signal. Range-bucket residual correction and command-grid alignment stay inside the calibration module, so they match the command format and evaluation protocol of PairUAV. On the UAVs in Multimedia 2026 PairUAV online evaluation, RASR reaches a total score of 0.003189. Under the PairUAV protocol, frozen pair geometry thus yields stable per-pair distance and heading estimates, while every protocol-specific adjustment stays confined to a calibration module fixed before inference. Code and materials are available at [https:](https:)//[github.com/lht-research/rasr-pairuav](github.com/lht-research/rasr-pairuav).  \nCCS Concepts  \n• Computing methodologies → Computer vision problems; • Computer systems organization → Robotic control.  \nKeywords  \nMetric UAV Navigation, Scale Recovery, Range-Aware Calibration, Relative Pose Estimation  \n1 Introduction  \nReaching a visual goal under Global Navigation Satellite System (GNSS) denial is a last-meter navigation problem in autonomous landing, aerial delivery, and search and rescue [1–5] . In this setting, an unmanned aerial vehicle (UAV) with a monocular camera can observe the target scene, but its observations do not directly specify metric scale. The UAVs in Multimedia (UAVM) 2026 PairUAV challenge turns this setting into target-driven relative pose estimation, where an ordered image pair must be converted into the heading and distance that move the agent toward the goal view [6, 7] . The required output is therefore an executable metric command for the controller, not a retrieval label.  \nDense pair-geometry models are a natural starting point for producing such commands. Dense and Unconstrained Stereo 3D Reconstruction (DUSt3R) and Matching And Stereo 3D Reconstruction (MASt3R) [8, 9] transfer to aerial pairs and encode pairwise structure. This structure, however, is not yet a displacement the controller can act on, and scale recovery bridges the gap to metric commands. In PairUAV, the raw metric outputs leave distance almost uncalibrated, whereas descriptor calibration removes most of that error.  \nGlobal scale recovery, though, calibrates only the average scale of the descriptor and cannot keep residuals equally acceptable across all ranges. Under the relative error evaluation in PairUAV, the same absolute distance error is compressed at long range but becomes critical near the goal, matching the","cbCaieyKDbv96RSg","https://ap.wps.com/l/cbCaieyKDbv96RSg","pdf",769610,1,5,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What problem does RASR solve in GNSS-denied metric UAV navigation?\",\"answer\":\"RASR addresses last-meter navigation where a UAV controller needs executable metric distance and heading commands despite the absence of GNSS. It focuses on improving the metric scale and reducing range-dependent residual errors near the goal view.\"},{\"question\":\"Why do PairUAV dense pair-geometry models require additional scale recovery?\",\"answer\":\"Dense pair-geometry models transfer relative structure, but their raw metric outputs remain poorly calibrated in distance scale. Even after average scale correction, systematic residuals persist and can be critical under PairUAV’s relative error evaluation.\"},{\"question\":\"How does RASR separate reusable computation from protocol-specific calibration?\",\"answer\":\"RASR separates a transferable scale-recovery core from a calibration module tailored to the PairUAV command format. Range-bucket residual correction and command-grid alignment are kept inside the protocol-specific module and are frozen before official inference.\"}]",1784205840,13,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"rasr-range-aware-scale-recovery-for-metric-uav-navigation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/rasr-range-aware-scale-recovery-for-metric-uav-navigation/85726/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does RASR solve in GNSS-denied metric UAV navigation?","Question",{"text":75,"@type":76},"RASR addresses last-meter navigation where a UAV controller needs executable metric distance and heading commands despite the absence of GNSS. It focuses on improving the metric scale and reducing range-dependent residual errors near the goal view.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why do PairUAV dense pair-geometry models require additional scale recovery?",{"text":80,"@type":76},"Dense pair-geometry models transfer relative structure, but their raw metric outputs remain poorly calibrated in distance scale. Even after average scale correction, systematic residuals persist and can be critical under PairUAV’s relative error evaluation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does RASR separate reusable computation from protocol-specific calibration?",{"text":84,"@type":76},"RASR separates a transferable scale-recovery core from a calibration module tailored to the PairUAV command format. Range-bucket residual correction and command-grid alignment are kept inside the protocol-specific module and are frozen before official inference.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]