{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:55:47Z","timestamp":1784739347419,"version":"3.55.0"},"reference-count":150,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62376269"],"award-info":[{"award-number":["62376269"]}],"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":["61991423"],"award-info":[{"award-number":["61991423"]}],"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":["U1805264"],"award-info":[{"award-number":["U1805264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3552598","type":"journal-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T17:56:45Z","timestamp":1743530205000},"page":"15622-15642","source":"Crossref","is-referenced-by-count":20,"title":["A Survey on Self-Supervised Monocular Depth Estimation Based on Deep Neural Networks"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4015-1615","authenticated-orcid":false,"given":"Qiulei","family":"Dong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6792-0739","authenticated-orcid":false,"given":"Zhengming","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8517-3415","authenticated-orcid":false,"given":"Xiaolan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Technology in Geo-Spatial Information Processing and Application System and the National Key Laboratory of Microwave Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7007-203X","authenticated-orcid":false,"given":"Liting","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.784284"},{"key":"ref2","first-page":"1161","article-title":"Learning depth from single monocular images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Saxena"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.56"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00668"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00744"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3213546"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2988679"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs14092252"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref18","first-page":"12626","article-title":"Forget about the LiDAR: Self-supervised depth estimators with MED probability volumes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"GonzalezBello"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160741"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.089"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103441"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1582-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/s22145353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330944"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/vehicles6010013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12257"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_34"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01249"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636075"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00818"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322549"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3301711"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00697"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.208"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00791"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160657"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196781"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3221416"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130321"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793512"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044181"},{"key":"ref56","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00163"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100895"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3289051"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_33"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00871"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01255"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_13"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00083"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_27"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01250"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01575"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01004"},{"key":"ref74","first-page":"1","article-title":"Semantically-guided representation learning for self-supervised monocular depth","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Guizilini"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01142"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_4"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01241"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/sym11091066"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01551"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25401"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3107362"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00716"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00172"},{"key":"ref89","first-page":"54987","article-title":"Dynamo-depth: Fixing unsupervised depth estimation for dynamical scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00907"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548381"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00579"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00045"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793621"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3074306"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3069785"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01094"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3663570"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01000"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_20"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00012"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00073"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00044"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475287"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01527"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_19"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00273"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196723"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120670"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01313"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00390"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00225"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01003"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01524"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01257"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160534"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00678"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1177"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124079"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_41"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3062772"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02052"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00863"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref136","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":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.470"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref141","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3054609"},{"key":"ref149","first-page":"53","article-title":"Self-supervised learning of depth and camera motion from 360\u00b0 videos","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Wang"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982157"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/10947242.pdf?arnumber=10947242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:47:02Z","timestamp":1757353622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":150,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3552598","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}