{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:40:26Z","timestamp":1765546826392,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561441","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"5140-5146","source":"Crossref","is-referenced-by-count":23,"title":["Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation"],"prefix":"10.1109","author":[{"given":"Hemang","family":"Chawla","sequence":"first","affiliation":[{"name":"Navinfo Europe,The Advanced Research Lab,The Netherlands"}]},{"given":"Arnav","family":"Varma","sequence":"additional","affiliation":[{"name":"Navinfo Europe,The Advanced Research Lab,The Netherlands"}]},{"given":"Elahe","family":"Arani","sequence":"additional","affiliation":[{"name":"Navinfo Europe,The Advanced Research Lab,The Netherlands"}]},{"given":"Bahram","family":"Zonooz","sequence":"additional","affiliation":[{"name":"Navinfo Europe,The Advanced Research Lab,The Netherlands"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep attention-based classification network for robust depth prediction","author":"li","year":"2018","journal-title":"Asian Conference on Computer Vision (ACCV)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref36","first-page":"37","article-title":"Deep robust single image depth estimation neural network using scene understanding","author":"ren","year":"2019","journal-title":"CVPR Workshops"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_20"},{"key":"ref11","first-page":"503","article-title":"Robust semi-supervised monocular depth estimation with reprojected distances","author":"guizilini","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967677"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341243"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00907"},{"key":"ref15","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref18","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500512"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.05.029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"article-title":"Measuring the tendency of cnns to learn surface statistical regularities","year":"2017","author":"jo","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_50"},{"article-title":"Banet: Dense bundle adjustment network","year":"2018","author":"tang","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_56"},{"key":"ref1","first-page":"605","article-title":"Learning to localize using a lidar intensity map","author":"barsan","year":"2018","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref9","first-page":"35","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","author":"bian","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00348"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"Orb-slam: a versatile and accurate monocular slam system","volume":"31","author":"mur-artal","year":"2015","journal-title":"IEEE Transactions on Robotics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO49542.2019.8961430"},{"key":"ref24","first-page":"270","article-title":"Unsupervised monocular depth estimation with left-right consistency","author":"godard","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00114"},{"key":"ref23","first-page":"740","article-title":"Unsupervised cnn for single view depth estimation: Geometry to the rescue","author":"garg","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917177"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.05.016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340802"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561441.pdf?arnumber=9561441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:21:11Z","timestamp":1659482471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561441","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}