{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:02:50Z","timestamp":1784912570226,"version":"3.55.0"},"reference-count":135,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"HKUST PGS"},{"name":"HKUST-DJI Joint Innovation Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3444912","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T17:20:31Z","timestamp":1723828831000},"page":"10579-10596","source":"Crossref","is-referenced-by-count":250,"title":["Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3139-0799","authenticated-orcid":false,"given":"Mu","family":"Hu","sequence":"first","affiliation":[{"name":"HKUST, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4349-8297","authenticated-orcid":false,"given":"Wei","family":"Yin","sequence":"additional","affiliation":[{"name":"Adelaide University, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2469-1316","authenticated-orcid":false,"given":"Zhipeng","family":"Cai","sequence":"additional","affiliation":[{"name":"Intel, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3386-8805","authenticated-orcid":false,"given":"Xiaoxiao","family":"Long","sequence":"additional","affiliation":[{"name":"HKU, Pok Fu Lam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-614X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"HKUST, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2710","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5573-2909","authenticated-orcid":false,"given":"Shaojie","family":"Shen","sequence":"additional","affiliation":[{"name":"HKUST, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868195"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01667"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"ref6","first-page":"25018","article-title":"MonoSDF: Exploring monocular geometric cues for neural implicit surface reconstruction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3313051"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00637"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00022"},{"key":"ref14","article-title":"PonderV2: Pave the way for 3D foundataion model with a universal pre-training paradigm","author":"Zhu","year":"2023"},{"key":"ref15","article-title":"Uni3D: Exploring unified 3D representation at scale","author":"Zhou","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref17","first-page":"3906","article-title":"New CRFs: Neural window fully-connected CRFs for monocular depth estimation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Yuan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3097396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00040"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00076"},{"key":"ref24","first-page":"730","article-title":"Single-image depth perception in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209968"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref29","first-page":"14128","article-title":"Hierarchical normalization for robust monocular depth estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00907"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_16"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01289"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00109"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref36","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023"},{"key":"ref37","first-page":"16558","article-title":"DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Teed"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01210"},{"key":"ref39","article-title":"Animatable neural implicit surfaces for creating avatars from videos","author":"Peng","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00873"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00037"},{"key":"ref42","article-title":"IronDepth: Iterative refinement of single-view depth using surface normal and its uncertainty","author":"Bae","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"ref44","article-title":"IEBins: Iterative elastic bins for monocular depth estimation","author":"Shao","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3164834"},{"key":"ref48","article-title":"DPSNet: End-to-end deep plane sweep stereo","author":"Im"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_19"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377712"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_40"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00822"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref60","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":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794101"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3020800"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298652"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00999"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_31"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3381710"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01261"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.173"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3330866"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_7"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_42"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01126"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00611"},{"key":"ref83","article-title":"The devil is in the labels: Semantic segmentation from sentences","author":"Yin","year":"2022"},{"key":"ref84","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref86","article-title":"DINOV2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref87","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00250"},{"key":"ref90","first-page":"589","article-title":"Mapillary planet-scale depth dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lopez-Antequera"},{"key":"ref91","article-title":"Investigating the impact of data normalization on classification performance","volume":"97","author":"Singh","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_44"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.642"},{"key":"ref98","article-title":"SURGE: Surface regularized geometry estimation from a single image","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Wang"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00077"},{"key":"ref101","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01839"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref104","article-title":"Vision transformers need registers","author":"Darcet","year":"2023"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"ref111","article-title":"DIODE: A dense indoor and outdoor depth dataset","author":"Vasiljevic","year":"2019"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01298"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref116","article-title":"Level 5 perception dataset 2020","author":"Kesten","year":"2019"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"ref118","article-title":"DIML\/CVL RGB-D dataset: 2M RGB-D images of natural indoor and outdoor scenes","author":"Cho","year":"2021"},{"key":"ref119","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0168-5"},{"key":"ref124","article-title":"Virtual KITTI 2","author":"Cabon","year":"2020"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref127","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref128","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136220"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_1"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2469274"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10638254.pdf?arnumber=10638254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:27:57Z","timestamp":1732667277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":135,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3444912","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":[[2024,12]]}}}