{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:26:28Z","timestamp":1775665588628,"version":"3.50.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010577","name":"Toyota Motor Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010577","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3628473","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:44:48Z","timestamp":1762195488000},"page":"2354-2367","source":"Crossref","is-referenced-by-count":14,"title":["UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7848-7325","authenticated-orcid":false,"given":"Luigi","family":"Piccinelli","sequence":"first","affiliation":[{"name":"ETH Zürich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1127-8887","authenticated-orcid":false,"given":"Christos","family":"Sakaridis","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zurich, Switzerland"}]},{"given":"Yung-Hsu","family":"Yang","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zurich, Switzerland"}]},{"given":"Mattia","family":"Segu","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zurich, Switzerland"}]},{"given":"Siyuan","family":"Li","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-6448","authenticated-orcid":false,"given":"Wim","family":"Abbeloos","sequence":"additional","affiliation":[{"name":"Toyota Motor Europe, Brussels, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3445-5711","authenticated-orcid":false,"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zurich, Switzerland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160741"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01173"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483203"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2602087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10384075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0109870"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref32","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref38","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01210"},{"key":"ref40","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_35"},{"key":"ref42","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_14"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00751"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3323858"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref48","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref50","article-title":"A2D2: Audi autonomous driving dataset","author":"Geyer","year":"2020"},{"key":"ref51","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wilson"},{"key":"ref52","article-title":"ARKitscenes - A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baruch"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00162"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref60","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ramakrishnan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102877"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref79","article-title":"Is my depth ground-truth good enough? HAMMER\u2013highly accurate multi-modal dataset for dense 3D scene regression","author":"Jung","year":"2022"},{"key":"ref80","article-title":"FLSea: Underwater visual-inertial and stereo-vision forward-looking datasets","author":"Randall","year":"2023"},{"key":"ref81","article-title":"From 2D to 3D: Re-thinking benchmarking of monocular depth prediction","author":"\u00d6rnek","year":"2022"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01592"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_1"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref87","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref88","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11224609.pdf?arnumber=11224609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:06:10Z","timestamp":1770671170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11224609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":88,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3628473","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}