{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:31:13Z","timestamp":1778081473497,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008122","name":"Institute of Information & communications Technology Planning & Evaluation (IITP)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008122","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811639","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"6511-6518","source":"Crossref","is-referenced-by-count":6,"title":["SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning"],"prefix":"10.1109","author":[{"given":"Jaehoon","family":"Choi","sequence":"first","affiliation":[{"name":"NAVER LABS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongki","family":"Jung","sequence":"additional","affiliation":[{"name":"NAVER LABS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghan","family":"Lee","sequence":"additional","affiliation":[{"name":"NAVER LABS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deokhwa","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER LABS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghwan","family":"Lee","sequence":"additional","affiliation":[{"name":"NAVER LABS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915620033"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560831"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967296"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060396"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01203"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793637"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969938"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561174"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341448"},{"key":"ref28","first-page":"103","article-title":"Depth estimation via affinity learned with convolutional spatial propagation network","author":"cheng","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref27","article-title":"Propagating confidences through cnns for sparse data regression","author":"eldesokey","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6635"},{"key":"ref2","first-page":"4009","article-title":"Adabins: Depth estimation using adaptive bins","author":"bhat","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/ROBOT.2007.364024","article-title":"A multi-state constraint Kalman filter for vision-aided inertial navigation","author":"mourikis","year":"2007","journal-title":"Proceedings 2007 IEEE International Conference on Robotics and Automation"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2853729"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989603"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460664"},{"key":"ref26","first-page":"1","article-title":"Sparse-to-dense: Depth prediction from sparse depth samples and a single image","author":"mal","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341161"},{"key":"ref50","first-page":"2017","article-title":"Spatial transformer networks","volume":"28","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TRO.2016.2597321","article-title":"On-manifold preintegration for real-time visual-inertial odometry","volume":"33","author":"forster","year":"2016","journal-title":"IEEE Transactions on Robotics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref11","article-title":"SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction","author":"choi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref13","first-page":"1","article-title":"Unsu-pervised Scale-consistent Depth Learning from Video","author":"bian","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340802"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635938"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01256"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1145\/3386569.3392377","article-title":"Consistent video depth estimation","volume":"39","author":"luo","year":"2020","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref19","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref8","first-page":"1851","article-title":"Unsupervised learning of depth and ego-motion from video","author":"zhou","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","author":"paszke","year":"2017","journal-title":"Automatic differentiation in pytorch"},{"key":"ref47","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196638"},{"key":"ref44","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"NIPS"},{"key":"ref43","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Deep Learning and Representation Learning Workshop NIPS"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811639.pdf?arnumber=9811639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:03:43Z","timestamp":1667516623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811639","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}