{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:26:14Z","timestamp":1775082374095,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSFC\/RGC Joint Research Scheme sponsored by the Research"},{"name":"Hong Kong Special Administrative Region, China"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HK RGC AoE"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tro.2026.3672482","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:41:02Z","timestamp":1773348062000},"page":"1535-1555","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Monocular 2-D and 3-D Perception of Endoluminal Scenes for Controlling Flexible Robotic Endoscopic Instruments"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7071-4135","authenticated-orcid":false,"given":"Ruofeng","family":"Wei","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5028-2603","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yui-Lun","family":"Ng","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9480-5845","authenticated-orcid":false,"given":"Yiyao","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6280-1135","authenticated-orcid":false,"given":"Justin Di-Lang","family":"Ho","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3370-7884","authenticated-orcid":false,"given":"Hon-Sing","family":"Tong","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4569-6948","authenticated-orcid":false,"given":"Xiaomei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2169-3374","authenticated-orcid":false,"given":"Jing","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1879-9730","authenticated-orcid":false,"given":"Ka-Wai","family":"Kwok","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3416-9950","authenticated-orcid":false,"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1776","article-title":"Intuitive gaze-control of a robotized flexible endoscope","volume-title":"Proc. IEEE Int. Conf. Intell. Rob. Syst.","author":"Oude","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.34133\/2020\/9724807"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rcs.2158"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2019.06.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231209338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2018.0034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3360950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1088\/2516-1091\/ab9f41"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3419649"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48058-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3354171"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3221368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijom.2023.05.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202370041"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3426953"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2022.3195027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101990"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_75"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/21681163.2020.1835546"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968568"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3008120"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197454"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487703"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062322-100607"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196596"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.314"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160287"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196779"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2023.3291022"},{"key":"ref34","first-page":"1336","article-title":"Learning eye-in-hand camera calibration from a single image","volume-title":"Proc. Conf. Rob. Learn.","author":"Valassakis","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.06.005"},{"key":"ref36","article-title":"Stereo correspondence and reconstruction of endoscopic data challenge","author":"Allan","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref39","article-title":"Endoufm: Utilizing foundation models for monocular depth estimation of endoscopic images","author":"Yao","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-05114-1_19"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_20"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_1"},{"key":"ref43","article-title":"Endoomni: Zero-shot cross-dataset depth estimation in endoscopy by robust self-learning from noisy labels","author":"Tian","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_16"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43999-5_48"},{"key":"ref47","first-page":"21273","article-title":"Lightdepth: Single-view depth self-supervision from illumination decline","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Rodruez-Puigvert","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref49","article-title":"Open-sourced reinforcement learning environments for surgical robotics","author":"Richter","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"ref51","article-title":"Sonogym: High performance simulation for challenging surgical tasks with robotic ultrasound","author":"Ao","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR67322.2025.11025977"},{"key":"ref53","first-page":"51","article-title":"Medical image segmentation with sam-generated annotations","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Hkkinen","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101900"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.254"},{"key":"ref57","first-page":"4884","article-title":"Probabilistic orientation estimation with matrix fisher distributions","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","volume":"33","author":"Mohlin","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-020-02161-8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_29"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"ref61","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102956"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/isbi48211.2021.9433780"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_27"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2023.3269856"},{"key":"ref72","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3199034"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01088"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref77","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref79","article-title":"Learning to efficiently adapt foundation models for self-supervised endoscopic 3D scene reconstruction from any cameras","author":"Cui","year":"2025"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_21"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1055\/a-0577-2798"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/8415_2012_125"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/11297026\/11429531.pdf?arnumber=11429531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:35Z","timestamp":1775074535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11429531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tro.2026.3672482","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}