{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:47:12Z","timestamp":1750747632361},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T00:00:00Z","timestamp":1660521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T00:00:00Z","timestamp":1660521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB2101300"],"award-info":[{"award-number":["2018YFB2101300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871186"],"award-info":[{"award-number":["61871186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Dean\u2019s Fund of Engineering Research Center of Software\/Hardware Co-design Technology and Application, Ministry of Education"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10489-022-04006-0","type":"journal-article","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T10:02:59Z","timestamp":1660557779000},"page":"10149-10161","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-supervised monocular depth estimation based on pseudo-pose guidance and grid regularization"],"prefix":"10.1007","volume":"53","author":[{"given":"Ying","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Weiting","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jiangtao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,15]]},"reference":[{"issue":"4","key":"4006_CR1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1145\/3386569.3392377","volume":"39","author":"X Luo","year":"2020","unstructured":"Luo X, Huang JB, Szeliski R, Matzen K, Kopf J (2020) Consistent video depth estimation. ACM Trans Graph (TOG) 39(4):71\u20131","journal-title":"ACM Trans Graph (TOG)"},{"key":"4006_CR2","doi-asserted-by":"crossref","unstructured":"Wang Y, Chao WL, Garg D, Hariharan B, Campbell M, Weinberger KQ (2019) Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8445\u20138453","DOI":"10.1109\/CVPR.2019.00864"},{"key":"4006_CR3","doi-asserted-by":"publisher","first-page":"106671","DOI":"10.1016\/j.knosys.2020.106671","volume":"213","author":"K Zhu","year":"2021","unstructured":"Zhu K, Jiang X, Fang Z, Gao Y, Fujita H, Hwang JN (2021) Photometric transfer for direct visual odometry. Knowl-Based Syst 213:106671","journal-title":"Knowl-Based Syst"},{"key":"4006_CR4","doi-asserted-by":"crossref","unstructured":"Guizilini V, Ambrus R, Pillai S, Raventos A, Gaidon A (2020) 3d Packing for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2485\u20132494","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"4006_CR5","doi-asserted-by":"crossref","unstructured":"Zhao C, Sun Q, Zhang C, Tang Y, Qian F (2020) Monocular depth estimation based on deep learning: an overview. Sci China Technol Sci, pp 1\u201316","DOI":"10.1007\/s11431-020-1582-8"},{"issue":"12","key":"4006_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42452-021-04882-0","volume":"3","author":"H Xu","year":"2021","unstructured":"Xu H, Liu N (2021) Detail-preserving depth estimation from a single image based on modified fully convolutional residual network and gradient network. SN Applied Sciences 3(12):1\u201315","journal-title":"SN Applied Sciences"},{"key":"4006_CR7","doi-asserted-by":"crossref","unstructured":"Godard C, Mac Aodha O, Firman M, Brostow GJ (2019) Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3828\u20133838","DOI":"10.1109\/ICCV.2019.00393"},{"key":"4006_CR8","first-page":"12626","volume":"33","author":"JL GonzalezBello","year":"2020","unstructured":"GonzalezBello JL, Kim M (2020) Forget about the lidar: Self-supervised depth estimators with med probability volumes. Adv Neural Inf Process Syst 33:12626\u201312637","journal-title":"Adv Neural Inf Process Syst"},{"key":"4006_CR9","doi-asserted-by":"publisher","unstructured":"Xue F, Zhuo G, Huang Z, Fu W, Wu Z, Ang MH (2020) Toward hierarchical self-supervised monocular absolute depth estimation for autonomous driving applications. In: 2020 IEEE\/RSJ International conference on intelligent robots and systems (IROS), pp 2330\u20132337. https:\/\/doi.org\/10.1109\/IROS45743.2020.9340802https:\/\/doi.org\/10.1109\/IROS45743.2020.9340802","DOI":"10.1109\/IROS45743.2020.9340802 10.1109\/IROS45743.2020.9340802"},{"key":"4006_CR10","doi-asserted-by":"crossref","unstructured":"Wu Z, Zhuo G, Xue F (2020) Self-supervised monocular depth estimation scale recovery using ransac outlier removal","DOI":"10.1109\/CVCI51460.2020.9338538"},{"key":"4006_CR11","doi-asserted-by":"publisher","first-page":"4691","DOI":"10.1109\/TIP.2021.3074306","volume":"30","author":"X Song","year":"2021","unstructured":"Song X, Li W, Zhou D, Dai Y, Fang J, Li H, Zhang L (2021) Mlda-net: Multi-level dual attention-based network for self-supervised monocular depth estimation. IEEE Trans Image Process 30:4691\u20134705","journal-title":"IEEE Trans Image Process"},{"key":"4006_CR12","doi-asserted-by":"crossref","unstructured":"Chen X, Wang Y, Chen X, Zeng W (2021) S2r-depthnet: Learning a generalizable depth-specific structural representation . In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3034\u20133043","DOI":"10.1109\/CVPR46437.2021.00305"},{"key":"4006_CR13","doi-asserted-by":"crossref","unstructured":"Kumar VR, Klingner M, Yogamani S, Milz S, Fingscheidt T, Mader P (2021) Syndistnet: Self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 61\u201371","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"4006_CR14","doi-asserted-by":"crossref","unstructured":"Klingner M, Term\u00f6hlen JA, Mikolajczyk J, Fingscheidt T (2020) Self-supervised monocular depth estimation: Solving the dynamic object problem by semantic guidance. In: European conference on computer vision, pp 582\u2013600. Springer","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"4006_CR15","doi-asserted-by":"crossref","unstructured":"Zhu S, Brazil G, Liu X (2020) The edge of depth: Explicit constraints between segmentation and depth. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13116\u201313125","DOI":"10.1109\/CVPR42600.2020.01313"},{"key":"4006_CR16","doi-asserted-by":"crossref","unstructured":"Garg R, Bg VK, Carneiro G, Reid I (2016) Unsupervised cnn for single view depth estimation: Geometry to the rescue. In: European conference on computer vision, pp 740\u2013756. Springer","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"4006_CR17","doi-asserted-by":"crossref","unstructured":"Godard C, Mac Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 270\u2013279","DOI":"10.1109\/CVPR.2017.699"},{"key":"4006_CR18","doi-asserted-by":"publisher","unstructured":"Li K, Fu Z, Wang H, Chen Z, Guo Y (2021) Adv-depth: Self-supervised monocular depth estimation with an adversarial loss. IEEE Signal Process Lett 28:638\u2013642. https:\/\/doi.org\/10.1109\/LSP.2021.3065203","DOI":"10.1109\/LSP.2021.3065203"},{"key":"4006_CR19","doi-asserted-by":"crossref","unstructured":"Zheng C, Cham TJ, Cai J (2018) T2net: Synthetic-to-realistic translation for solving single-image depth estimation tasks. In: Proceedings of the european conference on computer vision (ECCV), pp 767\u2013783","DOI":"10.1007\/978-3-030-01234-2_47"},{"key":"4006_CR20","doi-asserted-by":"crossref","unstructured":"Sattler T, Zhou Q, Pollefeys M, Leal-Taixe L (2019) Understanding the limitations of cnn-based absolute camera pose regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3302\u20133312","DOI":"10.1109\/CVPR.2019.00342"},{"key":"4006_CR21","first-page":"2017","volume":"28","author":"M Jaderberg","year":"2015","unstructured":"Jaderberg M, Simonyan K, Zisserman A et al (2015) Spatial transformer networks. Adv Neural Inf Process Syst 28:2017\u20132025","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"4006_CR22","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1109\/LRA.2018.2809549","volume":"3","author":"T Nguyen","year":"2018","unstructured":"Nguyen T, Chen SW, Shivakumar SS, Taylor CJ, Kumar V (2018) Unsupervised deep homography: a fast and robust homography estimation model. IEEE Robot Autom Lett 3(3):2346\u20132353","journal-title":"IEEE Robot Autom Lett"},{"issue":"12","key":"4006_CR23","doi-asserted-by":"publisher","first-page":"3420","DOI":"10.3390\/s20123420","volume":"20","author":"Y Tao","year":"2020","unstructured":"Tao Y, Ling Z (2020) Deep features homography transformation fusion network\u2014a universal foreground segmentation algorithm for ptz cameras and a comparative study. Sensors 20(12):3420","journal-title":"Sensors"},{"issue":"2","key":"4006_CR24","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60 (2):91\u2013110","journal-title":"Int J Comput Vis"},{"issue":"3","key":"4006_CR25","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (surf). Comput Vis Image Underst 110(3):346\u2013359","journal-title":"Comput Vis Image Underst"},{"key":"4006_CR26","doi-asserted-by":"crossref","unstructured":"Rublee E, Rabaud V, Konolige K, Bradski G (2011) Orb: an efficient alternative to sift or surf. In: 2011 International conference on computer vision, pp 2564\u20132571. Ieee","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"4006_CR27","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1109\/TCI.2021.3069785","volume":"7","author":"H Wang","year":"2021","unstructured":"Wang H, Sang X, Chen D, Wang P, Yan B, Qi S, Ye X, Yao T (2021) Self-supervised learning of monocular depth estimation based on progressive strategy. IEEE Trans Comput Imaging 7:375\u2013383","journal-title":"IEEE Trans Comput Imaging"},{"key":"4006_CR28","doi-asserted-by":"crossref","unstructured":"Li J, Hu Q, Ai M (2021) Point cloud registration based on one-point ransac and scale-annealing biweight estimation. IEEE Trans Geosci Remote Sens","DOI":"10.1109\/TGRS.2020.3045456"},{"issue":"4","key":"4006_CR29","doi-asserted-by":"publisher","first-page":"6618","DOI":"10.1109\/JIOT.2019.2909038","volume":"6","author":"YF Zhang","year":"2019","unstructured":"Zhang YF, Thorburn PJ, Xiang W, Fitch P (2019) Ssim\u2014a deep learning approach for recovering missing time series sensor data. IEEE Internet Things J 6(4):6618\u20136628","journal-title":"IEEE Internet Things J"},{"key":"4006_CR30","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.neucom.2020.02.022","volume":"399","author":"KL Yin","year":"2020","unstructured":"Yin KL, Pu YF, Lu L (2020) Combination of fractional flann filters for solving the van der pol-duffing oscillator. Neurocomputing 399:183\u2013192","journal-title":"Neurocomputing"},{"issue":"12","key":"4006_CR31","doi-asserted-by":"publisher","first-page":"4875","DOI":"10.1007\/s00170-019-03994-7","volume":"105","author":"N Wang","year":"2019","unstructured":"Wang N, He H (2019) Adaptive homography-based visual servo for micro unmanned surface vehicles. Int J Adv Manuf Technol 105(12):4875\u20134882","journal-title":"Int J Adv Manuf Technol"},{"key":"4006_CR32","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: The kitti dataset. Int J Robot Res (IJRR)","DOI":"10.1177\/0278364913491297"},{"key":"4006_CR33","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"4006_CR34","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1851\u20131858","DOI":"10.1109\/CVPR.2017.700"},{"key":"4006_CR35","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 32:8026\u20138037","journal-title":"Adv Neural Inf Process Syst"},{"key":"4006_CR36","doi-asserted-by":"crossref","unstructured":"Xiao J, Li H, Qu G, Fujita H, Cao Y, Zhu J, Huang C (2021) Hope: heatmap and offset for pose estimation. J Ambient Intell Humaniz Comput, pp 1\u201313","DOI":"10.1007\/s12652-021-03124-w"},{"key":"4006_CR37","doi-asserted-by":"crossref","unstructured":"Zhan H, Garg R, Weerasekera CS, Li K, Agarwal H, Reid I (2018) Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 340\u2013349","DOI":"10.1109\/CVPR.2018.00043"},{"key":"4006_CR38","doi-asserted-by":"crossref","unstructured":"Chen PY, Liu AH, Liu YC, Wang YCF (2019) Towards scene understanding: Unsupervised monocular depth estimation with semantic-aware representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2624\u20132632","DOI":"10.1109\/CVPR.2019.00273"},{"key":"4006_CR39","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.neucom.2020.11.002","volume":"423","author":"Z Lei","year":"2021","unstructured":"Lei Z, Wang Y, Li Z, Yang J (2021) Attention based multilayer feature fusion convolutional neural network for unsupervised monocular depth estimation. Neurocomputing 423:343\u2013352","journal-title":"Neurocomputing"},{"key":"4006_CR40","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04006-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04006-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04006-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T11:37:20Z","timestamp":1684496240000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04006-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,15]]},"references-count":40,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["4006"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04006-0","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,15]]},"assertion":[{"value":"13 July 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}