{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:07:23Z","timestamp":1780603643427,"version":"3.54.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","award":["UKRI914"],"award-info":[{"award-number":["UKRI914"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Academy of Medical Sciences through the Springboard Scheme","award":["SBF0010\\1191"],"award-info":[{"award-number":["SBF0010\\1191"]}]},{"name":"Oxford Branch of Ludwig Cancer Research and National Institute for Health Research (NIHR) Oxford Biomedical Research Centre"},{"name":"The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tmi.2026.3671423","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:58:10Z","timestamp":1773086290000},"page":"3203-3215","source":"Crossref","is-referenced-by-count":0,"title":["Self-Supervised Monocular Depth and Pose Estimation for Endoscopy With Latent Priors"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3883-3716","authenticated-orcid":false,"given":"Ziang","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Engineering, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4856-5014","authenticated-orcid":false,"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Leicester, Leicester, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"East","sequence":"additional","affiliation":[{"name":"Nuffield Department of Clinical Medicine, Experimental Medicine Division, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1313-3542","authenticated-orcid":false,"given":"Sharib","family":"Ali","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Leeds, Leeds, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8528-8298","authenticated-orcid":false,"given":"Jens","family":"Rittscher","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2021.0106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2208375"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.06.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32254-0_64"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-04247-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102956"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87231-1_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107619"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref12","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024","journal-title":"arXiv:2410.02073"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01962-w"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103379"},{"key":"ref15","first-page":"16558","article-title":"DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Teed"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102058"},{"key":"ref17","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref19","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019","journal-title":"arXiv:1907.10326"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00077"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/aad1e1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1117\/12.2513117"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/s21082691"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102338"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3352390"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3400804"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01945"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_20"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref38","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gulrajani"},{"key":"ref39","first-page":"1","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. ICLR (Poster)","author":"Higgins"},{"key":"ref40","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Kingma"},{"key":"ref41","article-title":"Learning energy-based variational latent prior for VAEs","author":"Dutta","year":"2025","journal-title":"arXiv:2510.00260"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44480-7_21"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103195"},{"key":"ref44","article-title":"SceneNet RGB-D: 5M photorealistic images of synthetic indoor trajectories with ground truth","author":"McCormac","year":"2016","journal-title":"arXiv:1612.05079"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11550367\/11427067.pdf?arnumber=11427067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:56:03Z","timestamp":1780602963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11427067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2026.3671423","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}