{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:48:42Z","timestamp":1768405722019,"version":"3.49.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62373298"],"award-info":[{"award-number":["62373298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3411688","type":"journal-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T17:32:33Z","timestamp":1718040753000},"page":"10604-10617","source":"Crossref","is-referenced-by-count":6,"title":["FS-Depth: Focal-and-Scale Depth Estimation From a Single Image in Unseen Indoor Scene"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8645-6165","authenticated-orcid":false,"given":"Chengrui","family":"Wei","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0525-5059","authenticated-orcid":false,"given":"Meng","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0370-177X","authenticated-orcid":false,"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1608-8257","authenticated-orcid":false,"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv:2302.12288"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816644364"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/1100000005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00273"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2018.05.005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-09538-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.260"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref12","article-title":"BinsFormer: Revisiting adaptive bins for monocular depth estimation","author":"Li","year":"2022","journal-title":"arXiv:2204.00987"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941776"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109982","article-title":"CATNet: Convolutional attention and transformer for monocular depth estimation","volume":"145","author":"Tang","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref21","first-page":"730","article-title":"Single-image depth perception in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3071682"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209968"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346466"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00996"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511807909"},{"issue":"1","key":"ref31","first-page":"154","article-title":"CCD vs. CMOS","volume":"35","author":"Litwiller","year":"2001","journal-title":"Photon Spectra"},{"key":"ref32","volume-title":"Digital Image Processing","author":"Gonzales","year":"1987"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01249"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2832296"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"ref37","article-title":"DIODE: A dense indoor and outdoor DEpth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv:1908.00463"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2836318"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01822"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00729"},{"key":"ref43","article-title":"Revealing the dark secrets of masked image modeling","author":"Xie","year":"2022","journal-title":"arXiv:2205.13543"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref46","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.","volume":"27","author":"Eigen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821979"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475386"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128505"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2772892"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2316835"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808682"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref59","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.05.029"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_41"},{"key":"ref63","first-page":"37","article-title":"Deep robust single image depth estimation neural network using scene understanding","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshops","volume":"2","author":"Ren"},{"key":"ref64","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00043"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00266"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768433\/10552238.pdf?arnumber=10552238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:14:24Z","timestamp":1736453664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10552238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":69,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3411688","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}