{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:11Z","timestamp":1783542491856,"version":"3.55.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U25A20536"],"award-info":[{"award-number":["U25A20536"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42595545"],"award-info":[{"award-number":["42595545"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of Chinese Academy of Sciences","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3667405","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:50:05Z","timestamp":1771879805000},"page":"9547-9560","source":"Crossref","is-referenced-by-count":0,"title":["ScaleDepth: Decomposing Metric Depth Estimation Into Semantic-Aware Scale Prediction and Adaptive Relative Depth Estimation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6092-0712","authenticated-orcid":false,"given":"Ruijie","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1431-7677","authenticated-orcid":false,"given":"Chuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6348-8713","authenticated-orcid":false,"given":"Ziyang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3280-8490","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7700-788X","authenticated-orcid":false,"given":"Jianfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2838-0378","authenticated-orcid":false,"given":"Jiacheng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023634"},{"key":"ref4","first-page":"1161","article-title":"Learning depth from single monocular images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Saxena"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102426"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.396"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref15","first-page":"730","article-title":"Single-image depth perception in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.52"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01822"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00729"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416065"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2307"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3335316"},{"key":"ref30","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv:2302.12288"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3411688"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00046"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821979"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120670"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2962867"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128505"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref46","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Han Lee","year":"2019","journal-title":"arXiv:1907.10326"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01243"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_13"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3476952"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01591"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00037"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3681436"},{"key":"ref58","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref59","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00218"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00550"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112475"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"ref70","article-title":"DIODE: A dense indoor and outdoor depth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv:1908.00463"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref72","article-title":"Virtual KITTI 2","author":"Cabon","year":"2020","journal-title":"arXiv:2001.10773"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref74","article-title":"DIML\/CVL RGB-D dataset: 2M RGB-D images of natural indoor and outdoor scenes","author":"Cho","year":"2021","journal-title":"arXiv:2110.11590"},{"key":"ref75","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref76","article-title":"Zero-shot metric depth with a field-of-view conditioned diffusion model","author":"Saxena","year":"2023","journal-title":"arXiv:2312.13252"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11408224.pdf?arnumber=11408224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:39Z","timestamp":1783539939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":80,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3667405","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}