{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:32:05Z","timestamp":1775745125167,"version":"3.50.1"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ONR","award":["N00014-19-S-B001"],"award-info":[{"award-number":["N00014-19-S-B001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020,10,1]]},"DOI":"10.1109\/tpami.2019.2930258","type":"journal-article","created":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T20:54:33Z","timestamp":1563915273000},"page":"2624-2641","source":"Crossref","is-referenced-by-count":200,"title":["Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6647-8283","authenticated-orcid":false,"given":"Chenxu","family":"Luo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0303-5885","authenticated-orcid":false,"given":"Zhenheng","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1265-0233","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Ram","family":"Nevatia","sequence":"additional","affiliation":[]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.238"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"ref71","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.21"},{"key":"ref77","first-page":"282","article-title":"Object segmentation by long term analysis of point trajectories","author":"brox","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1122-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298652"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460564"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.23"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.498"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2014.56"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.51"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.401"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28831-7_23"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref63","first-page":"4,10,13","article-title":"UnFlow: Unsupervised learning of optical flow with a bidirectional census loss","author":"meister","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref28","first-page":"834","article-title":"LSD-SLAM: Large-scale direct monocular SLAM","author":"engel","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00826"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790293"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.63"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0684-2"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.281"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.174"},{"key":"ref69","first-page":"757","article-title":"A continuous optimization approach for efficient and accurate scene flow","author":"lv","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref20","first-page":"38","article-title":"DF-Net: Unsupervised joint learning of depth and flow using cross-task consistency","author":"zou","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70752"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.14"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref50","first-page":"842","article-title":"Deep3D: Fully automatic 2D-to-3D video conversion with deep convolutional neural networks","author":"xie","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","first-page":"740","article-title":"Unsupervised CNN for single view depth estimation: Geometry to the rescue","author":"garg","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0006"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref11","first-page":"1,3,10","article-title":"Unsupervised learning of geometry from videos with edge-aware depth-normal consistency","author":"yang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref12","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref13","article-title":"VisualSFM: A visual structure from motion system","author":"wu","year":"2011"},{"key":"ref14","article-title":"SfM-Net: Learning of structure and motion from video","author":"vijayanarasimhan","year":"2017","journal-title":"arXiv preprint arXiv 1704 07804"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref16","first-page":"3","article-title":"Back to basics: Unsupervised learning of optical flow via brightness constancy and motion smoothness","author":"jason","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref81","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref17","first-page":"1495","article-title":"Unsupervised deep learning for optical flow estimation","author":"ren","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref80","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"ref3","first-page":"1","article-title":"Spatio-temporal action detection with cascade proposal and location anticipation","author":"yang","year":"2017","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"ref85","first-page":"1161","article-title":"Learning depth from single monocular images","author":"saxena","year":"2006","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref8","first-page":"691","article-title":"Every pixel counts: Unsupervised geometry learning with holistic 3D motion understanding","author":"yang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref86","first-page":"690","article-title":"Unsupervised learning of multi-frame optical flow with occlusions","author":"janai","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref49","first-page":"172","article-title":"SURGE: Surface regularized geometry estimation from a single image","author":"wang","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref45","first-page":"468","article-title":"Discriminatively trained dense surface normal estimation","author":"ladicky","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","first-page":"1119","article-title":"Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs","author":"li","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref42","first-page":"108","article-title":"Depth estimation via affinity learned with convolutional spatial propagation network","author":"cheng","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2316835"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9185119\/08769907.pdf?arnumber=8769907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:00:02Z","timestamp":1651068002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8769907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,1]]},"references-count":87,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2930258","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":[[2020,10,1]]}}}