{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:04:37Z","timestamp":1773486277939,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s10044-025-01584-w","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:39:01Z","timestamp":1764787141000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ORDMP: self-supervised monocular depth estimation via optical-flow-reconstructed directional masks and large-model teacher pseudo-labels"],"prefix":"10.1007","volume":"29","author":[{"given":"Shuwen","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongxiong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"1584_CR1","unstructured":"Bhat SF, Alhashim I, Wonka P (2021) Adabins: Depth estimation using adaptive bins. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p. 4009\u20134018"},{"key":"1584_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104520","volume":"125","author":"W Bingyuan","year":"2022","unstructured":"Bingyuan W, Wang Y (2022) Rich global feature guided network for monocular depth estimation. Image Vis Comput 125:104520","journal-title":"Image Vis Comput"},{"key":"1584_CR3","doi-asserted-by":"crossref","unstructured":"Agarwal A, Arora C (2023) Attention attention everywhere: Monocular depth prediction with skip attention. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, p. 5861\u20135870","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"1584_CR4","doi-asserted-by":"crossref","unstructured":"Piccinelli L, Sakaridis C, Yu F (2023) idisc: Internal discretization for monocular depth estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p. 21477\u201321487","DOI":"10.1109\/CVPR52729.2023.02057"},{"issue":"6","key":"1584_CR5","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s11633-023-1458-0","volume":"20","author":"Z Li","year":"2023","unstructured":"Li Z, Chen Z, Liu X, Jiang J (2023) Depthformer: Exploiting long-range correlation and local information for accurate monocular depth estimation. Mach Intell Res 20(6):837\u2013854","journal-title":"Mach Intell Res"},{"key":"1584_CR6","doi-asserted-by":"crossref","unstructured":"Jia S, Wang Y, Chen H, Huang S (2025) Svtnet: Dual branch of swin transformer and vision transformer for monocular depth estimation. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), p. 1\u20135. IEEE","DOI":"10.1109\/ICASSP49660.2025.10887818"},{"key":"1584_CR7","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Firman M, Brostow GJ (2019) Digging into self-supervised monocular depth estimation. In Proceedings of the IEEE\/CVF international conference on computer vision, p. 3828\u20133838","DOI":"10.1109\/ICCV.2019.00393"},{"key":"1584_CR8","doi-asserted-by":"crossref","unstructured":"Zhang N, Nex F, Vosselman G, Kerle N (2023) Lite-mono: A lightweight cnn and transformer architecture for self-supervised monocular depth estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p. 18537\u201318546","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"1584_CR9","doi-asserted-by":"crossref","unstructured":"Luginov A, Shahzad M (2024) Nimbled: Enhancing self-supervised monocular depth estimation with pseudo-labels and large-scale video pre-training. In European Conference on Computer Vision, p. 235\u2013251. Springer","DOI":"10.1007\/978-3-031-92387-6_18"},{"key":"1584_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3460868","author":"Y Feng","year":"2024","unstructured":"Feng Y, Guo Z, Chen Q, Fan R (2024) Scipad: incorporating spatial clues into unsupervised pose-depth joint learning. IEEE Trans Intell Veh. https:\/\/doi.org\/10.1109\/TIV.2024.3460868","journal-title":"IEEE Trans Intell Veh"},{"key":"1584_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110026","volume":"144","author":"X Qin","year":"2025","unstructured":"Qin X, Wang L, Zhu Y, Mao F, Zhang X, He C, Dong Q (2025) Rectified self-supervised monocular depth estimation loss for nighttime and dynamic scenes. Eng Appl Artif Intell 144:110026","journal-title":"Eng Appl Artif Intell"},{"key":"1584_CR12","doi-asserted-by":"crossref","unstructured":"Klingner M, Term\u00f6hlen J-A, Mikolajczyk J, Fingscheidt T (2020) Self-supervised monocular depth estimation: Solving the dynamic object problem by semantic guidance. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX 16, p. 582\u2013600. Springer","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"1584_CR13","doi-asserted-by":"crossref","unstructured":"Watson J, Mac\u00a0Aodha O, Prisacariu V, Brostow G, Firman M (2021) The temporal opportunist: Self-supervised multi-frame monocular depth. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p. 1164\u20131174","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"1584_CR14","doi-asserted-by":"crossref","unstructured":"Woo S, Lee W, Kim WJ, Lee D, Lee S (2024) Prodepth: Boosting self-supervised multi-frame monocular depth with probabilistic fusion. In European Conference on Computer Vision, p. 201\u2013217. Springer","DOI":"10.1007\/978-3-031-72646-0_12"},{"key":"1584_CR15","doi-asserted-by":"publisher","first-page":"6704","DOI":"10.1109\/LRA.2025.3568337","volume":"10","author":"K Zhou","year":"2025","unstructured":"Zhou K, Bian J-W, Zheng J-Q, Zhong J, Xie Q, Trigoni N, Markham A (2025) Manydepth2: Motion-aware self-supervised monocular depth estimation in dynamic scenes. IEEE Robot Autom Lett 10:6704\u20136711","journal-title":"IEEE Robot Autom Lett"},{"key":"1584_CR16","doi-asserted-by":"crossref","unstructured":"Yang L, Kang B, Huang Z, Xu X, Feng J, Zhao H (2024) Depth anything: Unleashing the power of large-scale unlabeled data. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p. 10371\u201310381","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"1584_CR17","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, p. 1851\u20131858","DOI":"10.1109\/CVPR.2017.700"},{"key":"1584_CR18","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, p. 2485\u20132494","DOI":"10.1109\/CVPR42600.2020.00256"},{"issue":"1","key":"1584_CR19","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1109\/TCSVT.2023.3284479","volume":"34","author":"C Feng","year":"2023","unstructured":"Feng C, Chen Z, Zhang C, Weiming H, Li B, Feng L (2023) Iterdepth: Iterative residual refinement for outdoor self-supervised multi-frame monocular depth estimation. IEEE Trans Circuits Syst Video Technol 34(1):329\u2013341","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1584_CR20","doi-asserted-by":"crossref","unstructured":"Wang Y, Liang Y, Hao X, Jiao S, Hongkai Yu (2024) Sqldepth: Generalizable self-supervised fine-structured monocular depth estimation. In Proceedings of the AAAI conference on artificial intelligence 38, p. 5713\u20135721","DOI":"10.1609\/aaai.v38i6.28383"},{"key":"1584_CR21","doi-asserted-by":"crossref","unstructured":"Saunders K, Vogiatzis G, Manso LJ (2023) Dyna-dm: Dynamic object-aware self-supervised monocular depth maps. In 2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), p. 10\u201316. IEEE","DOI":"10.1109\/ICARSC58346.2023.10129564"},{"key":"1584_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3609735","author":"S Wang","year":"2025","unstructured":"Wang S, Ren W, Gao P, Yu J, Liu J (2025) Zrid-net: Zero-reference real-world image dehazing framework via deep self-decoupling and reverse knowledge transfer. IEEE Trans Circuits Syst Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2025.3609735","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1584_CR23","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1109\/LSP.2025.3551201","volume":"32","author":"J Liu","year":"2025","unstructured":"Liu J, Pang Y, Wang S (2025) Dce-net: A dual-frequency domain knowledge-guided framework for image dehazing via detail and content enhancements. IEEE Signal Process Lett 32:1356\u20131360","journal-title":"IEEE Signal Process Lett"},{"issue":"3","key":"1584_CR24","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1007\/s00371-024-03511-2","volume":"41","author":"S Wang","year":"2025","unstructured":"Wang S, Hou Q, Li J, Liu J (2025) Tsid-net: a two-stage single image dehazing framework with style transfer and contrastive knowledge transfer. Vis Comput 41(3):1921\u20131938","journal-title":"Vis Comput"},{"key":"1584_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111997","volume":"160","author":"J Wang","year":"2025","unstructured":"Wang J, Wang S, Pang Y, Liu J (2025) Promptdnet: A weakly supervised prompt framework for single image dehazing via dual-level depth cues. Eng Appl Artif Intell 160:111997","journal-title":"Eng Appl Artif Intell"},{"issue":"4","key":"1584_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"1584_CR27","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In Proceedings of the IEEE conference on computer vision and pattern recognition, p. 270\u2013279","DOI":"10.1109\/CVPR.2017.699"},{"issue":"11","key":"1584_CR28","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: The kitti dataset. Int J Robot Res 32(11):1231\u20131237","journal-title":"Int J Robot Res"},{"key":"1584_CR29","doi-asserted-by":"crossref","unstructured":"Eigen D, Fergus R (2015) Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In Proceedings of the IEEE international conference on computer vision, p. 2650\u20132658","DOI":"10.1109\/ICCV.2015.304"},{"key":"1584_CR30","unstructured":"Cordts Marius, Omran Mohamed, Ramos Sebastian, Scharw\u00e4chter Timo, Enzweiler Markus, Benenson Rodrigo, Franke Uwe, Roth Stefan, Schiele Bernt (2015) The cityscapes dataset. In CVPR Workshop on the Future of Datasets in Vision 2:1"},{"key":"1584_CR31","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In Advances in neural information processing systems, 27"},{"key":"1584_CR32","doi-asserted-by":"crossref","unstructured":"Zhou J, Wang Y, Qin K, Zeng W (2019) Unsupervised high-resolution depth learning from videos with dual networks. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, p. 6872\u20136881","DOI":"10.1109\/ICCV.2019.00697"},{"key":"1584_CR33","unstructured":"Pnvr K, Zhou H, Jacobs D (2020) Sharingan: Combining synthetic and real data for unsupervised geometry estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p. 13974\u201313983"},{"key":"1584_CR34","doi-asserted-by":"crossref","unstructured":"Liu L, Song X, Wang M, Liu Y, Zhang L (2021) Self-supervised monocular depth estimation for all day images using domain separation. In Proceedings of the IEEE\/CVF international conference on computer vision, p. 12737\u201312746","DOI":"10.1109\/ICCV48922.2021.01250"},{"key":"1584_CR35","doi-asserted-by":"crossref","unstructured":"Liu Z, Song C, Cheng J, Luo J, Wang X (2024) Self-supervised monocular depth estimation with effective feature fusion and self distillation. In 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), p. 7160\u20137166. IEEE","DOI":"10.1109\/IROS58592.2024.10802237"},{"key":"1584_CR36","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1109\/TIP.2023.3338053","volume":"33","author":"G Li","year":"2023","unstructured":"Li G, Huang R, Li H, You Z, Chen W (2023) Sense: Self-evolving learning for self-supervised monocular depth estimation. IEEE Trans Image Process 33:439\u2013450","journal-title":"IEEE Trans Image Process"},{"key":"1584_CR37","doi-asserted-by":"publisher","first-page":"3548","DOI":"10.1109\/TETCI.2025.3547851","volume":"9","author":"S Wang","year":"2025","unstructured":"Wang S, Yu T, Pan S, Chen W, Wang Z, Leung VCM, Tian Z (2025) Latent object embedding for self-supervised monocular depth estimation. IEEE Trans Emerg Topics Comput Intell 9:3548\u20133559","journal-title":"IEEE Trans Emerg Topics Comput Intell"},{"key":"1584_CR38","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3577819","volume":"74","author":"S Yuan","year":"2025","unstructured":"Yuan S, Liu H, Liu Y, Yang L (2025) Self-supervised monocular depth estimation with depth-motion prior for pseudo-lidar. IEEE Trans Instrum Meas 74:5036415","journal-title":"IEEE Trans Instrum Meas"},{"key":"1584_CR39","doi-asserted-by":"crossref","unstructured":"Lee Seokju, Im Sunghoon, Lin Stephen, Kweon In So (2021) Learning monocular depth in dynamic scenes via instance-aware projection consistency. In Proceedings of the AAAI conference on artificial intelligence 35, p. 1863\u20131872","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"1584_CR40","doi-asserted-by":"crossref","unstructured":"Feng Z, Yang L, Jing L, Wang H, Tian Y, Li B (2022) Disentangling object motion and occlusion for unsupervised multi-frame monocular depth. In European Conference on Computer Vision, p. 228\u2013244. Springer","DOI":"10.1007\/978-3-031-19824-3_14"},{"key":"1584_CR41","doi-asserted-by":"crossref","unstructured":"Elazab G, Gr\u00e4ber T, Unterreiner M, Hellwich O (2025) Monopp: Metric-scaled self-supervised monocular depth estimation by planar-parallax geometry in automotive applications. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), p. 2777\u20132787. IEEE","DOI":"10.1109\/WACV61041.2025.00275"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01584-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-025-01584-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01584-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T10:38:20Z","timestamp":1773484700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-025-01584-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["1584"],"URL":"https:\/\/doi.org\/10.1007\/s10044-025-01584-w","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"26 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1"}}