[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82999-en":3,"doc-seo-82999-105":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},82999,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Observation Quality Matters Robust Multi Fisheye Calibration via Failure Oriented Analysis","Reliable calibration of multi-fisheye camera systems remains challenging as rig size, camera arrangement diversity, and field of view increase. Existing pipelines jointly optimize intrinsics, extrinsics, and target poses, yet success depends on the quality of supplied observations. A failure-oriented analysis shows failures are not mainly caused by detector recall loss or global image-plane imbalance. Instead, intrinsic initialization is the dominant factor: limited radial span couples focal scale with fisheye projection-shape parameters, yielding ill-conditioned updates.","Observation Quality Matters: Robust Multi-Fisheye Calibration via Failure-Oriented Analysis  \nPeize Liu 1 , Zhe Tong 1 , Chen Feng 1 ,†, and Shaojie Shen 1  \narXiv :2607 .05777v 1 [ cs .RO] 7 Jul 2026  \nAbstract—Reliable calibration of multi-fisheye camera systems remains challenging as rig size, camera arrangement diversity, and field of view increase. Existing pipelines can jointly optimize intrinsics, extrinsics, and target poses, but their success still depends heavily on empirical capture rules and the quality of the observations supplied to the solver. This paper studies this dependency through a failure-oriented analysis. We reveal that calibration failures are not sufficiently explained by detector recall loss or global image-plane distribution imbalance. Instead, the dominant failure factor lies in intrinsic initialization: observations with limited radial span couple focal scale with fisheye projection-shape parameters, producing ill-conditioned updates. Guided by this insight, we propose CO-Calib, a plugin calibration-data construction framework that combines a robust learning-based target detector with an error-analysisguided frame selector. CO-Calib constructs initialization-friendly anchors, co-visible multi-camera constraints, and coveragecompletion frames without changing the existing calibration workflow or optimization backend. Extensive experiments on synthetic and real multi-fisheye systems demonstrate that COCalib improves the overall success rate from 68.1% to 99.3%, increases extrinsic accuracy, and augments real-world calibration stability. The source code will be made publicly available at [https://github.com/HKUST-Aerial-Robotics/CO-Calib](https://github.com/HKUST-Aerial-Robotics/CO-Calib).  \nI. INTRODUCTION  \nMULTI-FISHEYE camera systems equipped with large  \nfield-of-view (FoV) lenses are widely used in mobile robots [1], [2] and data collection platforms [3], [4], where they improve perception performance in tasks such as state estimation [5] and depth prediction [6], [7] . Yet robust calibration of such systems remains challenging. As the number of cameras, their spatial arrangement, and the covered FoV increase, the underlying bundle-adjustment (BA) problem becomes larger and more tightly coupled. Meanwhile, accurate calibration requires reliable observations over a broader and more distorted image domain, making the optimization increasingly sensitive to the quality and distribution of the observations supplied to the solver.  \nThis observation sensitivity is particularly evident in industrial workflows. Different rig configurations are often calibrated with tailored procedures that prescribe capture trajectories, per-camera sampling requirements, and sometimes even dedicated calibration targets such as 3D or spherical patterns. As a result, seemingly minor changes in this process can induce noticeably different outcomes or calibration failure, leading to repeated engineering effort and limited robustness across platforms.  \n1Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China.  \nEmail: {pliuan, ztongae, cfengag, [eeshaojie](eeshaojie}@ust.hk)[}](eeshaojie}@ust.hk)[@ust.hk](eeshaojie}@ust.hk)[ ](eeshaojie}@ust.hk)†Corresponding Author  \nExisting multi-fisheye calibration methods, such as Kalibr [8], typically follow a representative pipeline that progressively initializes and refines camera intrinsics, per-view target poses, and inter-camera extrinsics. Subsequent studies improve calibration from different perspectives, for example by boosting intrinsic estimation under severe distortion [9] or by strengthening geometric constraints through richer calibration targets [10] . Taken together, these works reveal that calibration performance is governed not only by the nonlinear BAsolver, but depends critically on the observations on which the solver operates. However, observation quality is still treated largely in an implicit and e","cbCaitt5QDWqVdWv","https://ap.wps.com/l/cbCaitt5QDWqVdWv","pdf",24154644,1,9,"English","en",105,"# Introduction\n## Observation sensitivity in multi-fisheye calibration\n## Existing methods and the gap\n## Failure-oriented analysis and key finding\n## Proposed CO-Calib approach","[{\"question\":\"Why do multi-fisheye calibration pipelines often fail despite good optimization routines?\",\"answer\":\"Calibration failures depend strongly on observation quality; they are not sufficiently explained by detector recall loss or global image-plane distribution imbalance.\"},{\"question\":\"What is the dominant failure factor identified by the failure-oriented analysis?\",\"answer\":\"The dominant factor is intrinsic initialization: observations with limited radial span couple focal scale with fisheye projection-shape parameters, making updates ill-conditioned.\"},{\"question\":\"How does CO-Calib improve calibration without changing the existing workflow backend?\",\"answer\":\"CO-Calib builds calibration data via a learning-based target detector and an error-analysis-guided frame selector, creating initialization-friendly anchors, stronger co-visible multi-camera constraints, and coverage-completion frames.\"}]",1784184566,23,{"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},"observation-quality-matters-robust-multi-fisheye-calibration-via-failure-oriented-analysis","",{"@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/observation-quality-matters-robust-multi-fisheye-calibration-via-failure-oriented-analysis/82999/",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},"Why do multi-fisheye calibration pipelines often fail despite good optimization routines?","Question",{"text":75,"@type":76},"Calibration failures depend strongly on observation quality; they are not sufficiently explained by detector recall loss or global image-plane distribution imbalance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the dominant failure factor identified by the failure-oriented analysis?",{"text":80,"@type":76},"The dominant factor is intrinsic initialization: observations with limited radial span couple focal scale with fisheye projection-shape parameters, making updates ill-conditioned.",{"name":82,"@type":73,"acceptedAnswer":83},"How does CO-Calib improve calibration without changing the existing workflow backend?",{"text":84,"@type":76},"CO-Calib builds calibration data via a learning-based target detector and an error-analysis-guided frame selector, creating initialization-friendly anchors, stronger co-visible multi-camera constraints, and coverage-completion frames.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},"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":106,"slug":137},19,"General","general"]