{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:24:44Z","timestamp":1740122684518,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s10489-023-04851-7","type":"journal-article","created":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T03:18:02Z","timestamp":1690600682000},"page":"24804-24821","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Relative order constraint for monocular depth estimation"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5463-0807","authenticated-orcid":false,"given":"Chunpu","family":"Liu","sequence":"first","affiliation":[]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[]},{"given":"Guanglei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Wanlong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Hongbo","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Tianyi","family":"Zang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,29]]},"reference":[{"key":"4851_CR1","doi-asserted-by":"crossref","unstructured":"Eigen D, Fergus R (2015) \u201cPredicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture.\u201d In Proceedings of the IEEE international conference on computer vision, pp 2650\u20132658","DOI":"10.1109\/ICCV.2015.304"},{"key":"4851_CR2","doi-asserted-by":"crossref","unstructured":"Laina I, Rupprecht C, Belagiannis V, Tombari F, Navab N (2016) \u201cDeeper depth prediction with fully convolutional residual networks,\u201d In 2016 Fourth international conference on 3D vision (3DV), pp 239\u2013248. IEEE","DOI":"10.1109\/3DV.2016.32"},{"key":"4851_CR3","doi-asserted-by":"crossref","unstructured":"Fu H, Gong M, Wang C, Batmanghelich K, Tao D (2018) \u201cDeep ordinal regression network for monocular depth estimation.\u201d In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2002\u20132011","DOI":"10.1109\/CVPR.2018.00214"},{"key":"4851_CR4","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) \u201cAttention is all you need.\u201d Adv Neural Inf Process Syst 30"},{"key":"4851_CR5","doi-asserted-by":"crossref","unstructured":"Yuan W, Gu X, Dai Z, Zhu S, Tan P (2022) \u201cNewcrfs: Neural window fully-connected crfs for monocular depth estimation.\u201d In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"4851_CR6","unstructured":"Kim D, Ga W, Ahn P, Joo D, Chun S, Kim J (2022) \u201cGlobal-local path networks for monocular depth estimation with vertical cutdepth.\u201d arXiv:2201.07436"},{"key":"4851_CR7","unstructured":"Lee JH, Han MK, Ko DW, Suh IH (2019) \u201cFrom big to small: Multi-scale local planar guidance for monocular depth estimation.\u201d arXiv:1907.10326"},{"key":"4851_CR8","doi-asserted-by":"crossref","unstructured":"Qi X, Liao R, Liu Z, Urtasun R, Jia J (2018) \u201cGeonet: geometric neural network for joint depth and surface normal estimation.\u201d In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 283\u2013291","DOI":"10.1109\/CVPR.2018.00037"},{"key":"4851_CR9","doi-asserted-by":"crossref","unstructured":"Yin W, Liu Y, Shen C, Yan Y, (2019) \u201cEnforcing geometric constraints of virtual normal for depth prediction.\u201d In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 5684\u20135693","DOI":"10.1109\/ICCV.2019.00578"},{"key":"4851_CR10","unstructured":"Eigen D, Puhrsch C, Fergus R (2014)\u201cDepth map prediction from a single image using a multi-scale deep network.\u201d Adv Neural Inf Process Syst 27"},{"key":"4851_CR11","doi-asserted-by":"crossref","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012)\u201cIndoor segmentation and support inference from rgbd images.\u201d In European conference on computer vision, pp 746\u2013760. Springer","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"4851_CR12","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. Int J Robot Res 32(11):1231\u20131237","DOI":"10.1177\/0278364913491297"},{"key":"4851_CR13","doi-asserted-by":"crossref","unstructured":"Masoumian A, Rashwan HA, Cristiano J, Asif MS, Puig D (2022) Monocular depth estimation using deep learning: a review. Sensors 22(14):5353","DOI":"10.3390\/s22145353"},{"key":"4851_CR14","unstructured":"Vyas P, Saxena C, Badapanda A, Goswami A (2022) \u201cOutdoor monocular depth estimation: a research review.\u201d arXiv:2205.01399"},{"key":"4851_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) \u201cDeep residual learning for image recognition.\u201d In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"4851_CR16","doi-asserted-by":"crossref","unstructured":"Xu D, Ricci E, Ouyang W, Wang X, Sebe N (2017) \u201cMulti-scale continuous crfs as sequential deep networks for monocular depth estimation.\u201d In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5354\u20135362","DOI":"10.1109\/CVPR.2017.25"},{"issue":"6","key":"4851_CR17","first-page":"1426","volume":"41","author":"E Ricci","year":"2018","unstructured":"Ricci E, Ouyang W, Wang X, Sebe N et al (2018) Monocular depth estimation using multi-scale continuous crfs as sequential deep networks. IEEE Trans Pattern Anal Mach Intell 41(6):1426\u20131440","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"4851_CR18","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1109\/TCSVT.2017.2740321","volume":"28","author":"Y Cao","year":"2017","unstructured":"Cao Y, Wu Z, Shen C (2017) Estimating depth from monocular images as classification using deep fully convolutional residual networks. IEEE Trans Circuits Syst Video Technol 28(11):3174\u20133182","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4851_CR19","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) \u201cAn image is worth 16x16 words: transformers for image recognition at scale.\u201d In International Conference on Learning Representations"},{"key":"4851_CR20","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) \u201cSwin transformer: hierarchical vision transformer using shifted windows.\u201d In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 10\u00a0012\u201310\u00a0022","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"1","key":"4851_CR21","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y et al (2022) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 45(1):87\u2013110","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4851_CR22","unstructured":"Bhat SF, Alhashim I, Wonka P (2021) \u201cAdabins: depth estimation using adaptive bins.\u201d In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4009\u20134018"},{"key":"4851_CR23","unstructured":"Ranftl R, Lasinger K, Hafner D, Schindler K, Koltun V (2020) \u201cTowards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer.\u201d IEEE Trans Pattern Anal Mach Intell (TPAMI)"},{"key":"4851_CR24","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1016\/j.neucom.2022.01.005","volume":"493","author":"Y Mo","year":"2022","unstructured":"Mo Y, Wu Y, Yang X, Liu F, Liao Y (2022) Review the state-of-the-art technologies of semantic segmentation based on deep learning. Neurocomputing 493:626\u2013646","journal-title":"Neurocomputing"},{"key":"4851_CR25","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhou W, Lv Q, Yao G (2022) \u201cMetricmask: single category instance segmentation by metric learning.\u201d Neurocomputing","DOI":"10.1016\/j.neucom.2022.05.117"},{"key":"4851_CR26","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1016\/j.neucom.2022.04.042","volume":"492","author":"B Gao","year":"2022","unstructured":"Gao B, Zhao Y, Zhang F, Luo B, Yang C (2022) Video object segmentation based on multi-level target models and feature integration. Neurocomputing 492:396\u2013407","journal-title":"Neurocomputing"},{"key":"4851_CR27","doi-asserted-by":"crossref","unstructured":"Zhang Z, Cui Z, Xu C, Jie Z, Li X, Yang J (2018) \u201cJoint task-recursive learning for semantic segmentation and depth estimation.\u201d In Proceedings of the European Conference on Computer Vision (ECCV), pp 235\u2013251","DOI":"10.1007\/978-3-030-01249-6_15"},{"issue":"9","key":"4851_CR28","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.3390\/s20092567","volume":"20","author":"Dh Kwak","year":"2022","unstructured":"Kwak Dh, Lee Sh (2022) A novel method for estimating monocular depth using cycle gan and segmentation. Sensors 20(9):2567","journal-title":"Sensors"},{"key":"4851_CR29","doi-asserted-by":"crossref","unstructured":"He L, Lu J, Wang G, Song S, Zhou J (2021) Sosd-net: joint semantic object segmentation and depth estimation from monocular images. Neurocomputing 440:251\u2013263","DOI":"10.1016\/j.neucom.2021.01.126"},{"key":"4851_CR30","doi-asserted-by":"crossref","unstructured":"Li R, Xue D, Su S, He X, Mao Q, Zhu Y, Sun J, Zhang Y (2023) \u201cLearning depth via leveraging semantics: self-supervised monocular depth estimation with both implicit and explicit semantic guidance.\u201d Pattern Recognit 109297","DOI":"10.1016\/j.patcog.2022.109297"},{"key":"4851_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110184","volume":"260","author":"FE Benkirane","year":"2023","unstructured":"Benkirane FE, Crombez N, Ruichek Y, Hilaire V (2023) Integration of ontology reasoning-based monocular cues in deep learning modeling for single image depth estimation in urban driving scenarios. Knowl-Based Syst 260:110184","journal-title":"Knowl-Based Syst"},{"key":"4851_CR32","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) \u201cUnsupervised learning of depth and ego-motion from video.\u201d In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1851\u20131858","DOI":"10.1109\/CVPR.2017.700"},{"key":"4851_CR33","doi-asserted-by":"crossref","unstructured":"Zhan H, Garg R, Weerasekera CS, Li K, Agarwal H, Reid I (2018) \u201cUnsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction.\u201d In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 340\u2013349","DOI":"10.1109\/CVPR.2018.00043"},{"key":"4851_CR34","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Firman M, Brostow GJ (2019) \u201cDigging into self-supervised monocular depth estimation.\u201d In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 3828\u20133838","DOI":"10.1109\/ICCV.2019.00393"},{"issue":"5","key":"4851_CR35","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1109\/TETCI.2022.3182360","volume":"6","author":"C Zhao","year":"2022","unstructured":"Zhao C, Tang Y, Sun Q (2022) Unsupervised monocular depth estimation in highly complex environments. IEEE Trans Emerg Topics Comput Intell 6(5):1237\u20131246","journal-title":"IEEE Trans Emerg Topics Comput Intell"},{"key":"4851_CR36","doi-asserted-by":"crossref","unstructured":"Zhou Z, Dong Q (2022) \u201cSelf-distilled feature aggregation for self-supervised monocular depth estimation.\u201d In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part I, pp 709\u2013726. Springer","DOI":"10.1007\/978-3-031-19769-7_41"},{"key":"4851_CR37","doi-asserted-by":"crossref","unstructured":"Masoumian A, Rashwan HA, Abdulwahab S, Cristiano J, Asif MS, Puig D (2023) Gcndepth: self-supervised monocular depth estimation based on graph convolutional network. Neurocomputing 517:81\u201392","DOI":"10.1016\/j.neucom.2022.10.073"},{"key":"4851_CR38","doi-asserted-by":"crossref","unstructured":"He M, Hui L, Bian Y, Ren J, Xie J, Yang J (2022) \u201cRa-depth: resolution adaptive self-supervised monocular depth estimation.\u201d In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXVII, pp 565\u2013581. Springer","DOI":"10.1007\/978-3-031-19812-0_33"},{"key":"4851_CR39","doi-asserted-by":"crossref","unstructured":"Wofk D, Ma F, Yang TJ, Karaman S, Sze V (2019) \u201cFastdepth: fast monocular depth estimation on embedded systems.\u201d In 2019 International Conference on Robotics and Automation (ICRA), pp 6101\u20136108. IEEE","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"4851_CR40","doi-asserted-by":"crossref","unstructured":"Liu X, Wei W, Liu C, Peng Y, Huang J, Li J (2023) \u201cReal-time monocular depth estimation merging vision transformers on edge devices for aiot.\u201d IEEE Trans Instrum Meas","DOI":"10.1109\/TIM.2023.3264039"},{"key":"4851_CR41","doi-asserted-by":"crossref","unstructured":"Dong X, Garratt MA, Anavatti SG, Abbass HA (2022) \u201cTowards real-time monocular depth estimation for robotics: a survey.\u201d IEEE Trans Intell Transport Syst 23(10):16\u00a0940\u201316\u00a0961","DOI":"10.1109\/TITS.2022.3160741"},{"key":"4851_CR42","doi-asserted-by":"crossref","unstructured":"Liu Y, Chen K, Liu C, Qin Z, Luo Z, Wang J (2019) \u201cStructured knowledge distillation for semantic segmentation.\u201d In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2604\u20132613","DOI":"10.1109\/CVPR.2019.00271"},{"key":"4851_CR43","doi-asserted-by":"crossref","unstructured":"Wang K, Zhang Z, Yan Z, Li X, Xu B, Li J, Yang J (2021) \u201cRegularizing nighttime weirdness: efficient self-supervised monocular depth estimation in the dark.\u201d In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 16\u00a0055\u201316\u00a0064","DOI":"10.1109\/ICCV48922.2021.01575"},{"key":"4851_CR44","doi-asserted-by":"crossref","unstructured":"Ranftl R, Lasinger K, Hafner D, Schindler K, Koltun V (2020) Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans Pattern Analysis Machine Intell 44(3):1623\u20131637","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"4851_CR45","unstructured":"Chen W, Fu Z, Yang D, Deng J (2016) \u201cSingle-image depth perception in the wild.\u201d Adv Neural Inf Process Syst 29"},{"key":"4851_CR46","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"},{"issue":"10","key":"4851_CR47","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2015","unstructured":"Liu F, Shen C, Lin G, Reid I (2015) Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell 38(10):2024\u20132039","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4851_CR48","doi-asserted-by":"crossref","unstructured":"Abdulwahab S, Rashwan HA, Garcia MA, Masoumian A, Puig D (2022) \u201cMonocular depth map estimation based on a multi-scale deep architecture and curvilinear saliency feature boosting.\u201d Neural Comput Appl 34(19):16\u00a0423\u201316\u00a0440","DOI":"10.1007\/s00521-022-07663-x"},{"issue":"11","key":"4851_CR49","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.1109\/TCSVT.2021.3049869","volume":"31","author":"M Song","year":"2021","unstructured":"Song M, Lim S, Kim W (2021) Monocular depth estimation using laplacian pyramid-based depth residuals. IEEE Trans Circuits Systems Video Technol 31(11):4381\u20134393","journal-title":"IEEE Trans Circuits Systems Video Technol"},{"key":"4851_CR50","doi-asserted-by":"crossref","unstructured":"Meng X, Fan C, Ming Y, Yu H (2021) Cornet: context-based ordinal regression network for monocular depth estimation. IEEE Trans Circuits Systr Video Technol 32(7):4841\u20134853","DOI":"10.1109\/TCSVT.2021.3128505"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04851-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-04851-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04851-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T14:10:56Z","timestamp":1698070256000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-04851-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,29]]},"references-count":50,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["4851"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-04851-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2023,7,29]]},"assertion":[{"value":"29 June 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflict of interest exits in the submission of this manuscript, and manuscript is approved by all authors for publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}