{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T02:14:37Z","timestamp":1786068877515,"version":"3.56.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Bourns Endowment Funds"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tcsvt.2022.3207105","type":"journal-article","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T19:38:08Z","timestamp":1663270688000},"page":"830-846","source":"Crossref","is-referenced-by-count":34,"title":["MonoIndoor++: Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9153-5796","authenticated-orcid":false,"given":"Runze","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of California at Riverside, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Ji","sequence":"additional","affiliation":[{"name":"OPPO US Research Center, InnoPeak Technology Inc., Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2126-6054","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"OPPO US Research Center, InnoPeak Technology Inc., Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8971-6416","authenticated-orcid":false,"given":"Bir","family":"Bhanu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Riverside, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00871"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136220"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref16","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915620033"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref23","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"arXiv:1406.2283","author":"Eigen","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.596"},{"key":"ref31","first-page":"1","article-title":"DeepV2D: Video to depth with differentiable structure from motion","volume-title":"Proc. ICLR","author":"Teed"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00465"},{"key":"ref34","first-page":"1","article-title":"DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras","volume-title":"Proc. NeurIPS","author":"Teed"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref38","first-page":"1","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume-title":"Proc. NeurIPS","author":"Bian"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00570"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_26"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"ref45","article-title":"Unsupervised depth learning in challenging indoor video: Weak rectification to rescue","volume-title":"arXiv:2006.02708","author":"Bian","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref47","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref50","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref51","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. NeurIPS","author":"Jaderberg"},{"key":"ref52","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref53","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. NeurIPS","author":"Qi"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref57","first-page":"1","article-title":"An intriguing failing of convolutional neural networks and the CoordConv solution","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080928"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"key":"ref62","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref63","first-page":"1","article-title":"Adam: A method for stochastic gradient descent","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2316835"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.97"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.19"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.594"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref71","first-page":"1","article-title":"Depth from a single image by harmonizing overcomplete local network predictions","volume-title":"Proc. NeurIPS","author":"Chakrabarti"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093334"},{"key":"ref73","first-page":"206","article-title":"P\u00b2 Net: Patch-match and plane-regularization for unsupervised indoor depth estimation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Yu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197374"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54190-7_20"},{"key":"ref76","article-title":"BA-Net: Dense bundle adjustment network","volume-title":"arXiv:1806.04807","author":"Tang","year":"2018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"ref78","article-title":"DRO: Deep recurrent optimizer for structure-from-motion","volume-title":"arXiv:2103.13201","author":"Gu","year":"2021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10036154\/09893171.pdf?arnumber=9893171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T20:57:00Z","timestamp":1705957020000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":80,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3207105","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}