{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:07:35Z","timestamp":1779235655806,"version":"3.51.4"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004750","name":"Chinese Aeronautical Establishment Aeronautical Science Foundation","doi-asserted-by":"publisher","award":["2024Z071075001"],"award-info":[{"award-number":["2024Z071075001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.asoc.2026.114705","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:54:30Z","timestamp":1769187270000},"page":"114705","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MFU-Depth: Modeling and fusing uncertainty for self-supervised multi-frame monocular depth estimation"],"prefix":"10.1016","volume":"191","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9183-9471","authenticated-orcid":false,"given":"Fuji","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1969-2161","authenticated-orcid":false,"given":"Jinfu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-7815","authenticated-orcid":false,"given":"Jiaqi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.114705_bib0005","doi-asserted-by":"crossref","first-page":"15622","DOI":"10.1109\/TNNLS.2025.3552598","article-title":"A survey on self-supervised monocular depth estimation based on deep neural networks","volume":"36","author":"Dong","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0010","doi-asserted-by":"crossref","first-page":"3955","DOI":"10.1109\/TASE.2023.3290348","article-title":"FSNet: redesign self-supervised monodepth for full-scale depth prediction for autonomous driving","volume":"21","author":"Liu","year":"2023","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.asoc.2026.114705_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.112809","article-title":"A tightly-coupled dense monocular visual-inertial odometry system with lightweight depth estimation network","volume":"171","author":"Wang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.114705_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1851","article-title":"Unsupervised learning of depth and ego-motion from video","author":"Zhou","year":"2017"},{"key":"10.1016\/j.asoc.2026.114705_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3828","article-title":"Digging into self-supervised monocular depth estimation","author":"Godard","year":"2019"},{"key":"10.1016\/j.asoc.2026.114705_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18537","article-title":"Lite-Mono: a lightweight CNN and transformer architecture for self-supervised monocular depth estimation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.asoc.2026.114705_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1164","article-title":"The temporal opportunist: self-supervised multi-frame monocular depth","author":"Watson","year":"2021"},{"key":"10.1016\/j.asoc.2026.114705_bib0040","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"228","article-title":"Disentangling object motion and occlusion for unsupervised multi-frame monocular depth","author":"Feng","year":"2022"},{"key":"10.1016\/j.asoc.2026.114705_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"160","article-title":"Multi-frame self-supervised depth with transformers","author":"Guizilini","year":"2022"},{"key":"10.1016\/j.asoc.2026.114705_bib0050","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"767","article-title":"MVSNet: depth inference for unstructured multi-view stereo","author":"Yao","year":"2018"},{"key":"10.1016\/j.asoc.2026.114705_bib0055","doi-asserted-by":"crossref","first-page":"12291","DOI":"10.1109\/LRA.2022.3214787","article-title":"Two-stream based multi-stage hybrid decoder for self-supervised multi-frame monocular depth","volume":"7","author":"Long","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.asoc.2026.114705_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113467","article-title":"IFDepth: iterative fusion network for multi-frame self-supervised monocular depth estimation","volume":"318","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0065","doi-asserted-by":"crossref","first-page":"17292","DOI":"10.1109\/TNNLS.2023.3301711","article-title":"Self-supervised monocular depth estimation with self-perceptual anomaly handling","volume":"35","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0070","doi-asserted-by":"crossref","first-page":"2564","DOI":"10.1109\/TCSVT.2023.3305776","article-title":"Ds-Depth: dynamic and static depth estimation via a fusion cost volume","volume":"34","author":"Miao","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.114705_bib0075","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"2553","article-title":"Multi-frame self-supervised depth estimation with multi-scale feature fusion in dynamic scenes","author":"Zhong","year":"2023"},{"key":"10.1016\/j.asoc.2026.114705_bib0080","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"7318","article-title":"Mal: motion-aware loss with temporal and distillation hints for self-supervised depth estimation","author":"Dong","year":"2024"},{"key":"10.1016\/j.asoc.2026.114705_bib0085","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3477140","article-title":"A survey on uncertainty estimation in deep learning classification systems from a Bayesian perspective","volume":"54","author":"Mena","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.asoc.2026.114705_bib0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3227","article-title":"On the uncertainty of self-supervised monocular depth estimation","author":"Poggi","year":"2020"},{"key":"10.1016\/j.asoc.2026.114705_bib0095","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"3637","article-title":"Monoprob: self-supervised monocular depth estimation with interpretable uncertainty","author":"Marsal","year":"2024"},{"key":"10.1016\/j.asoc.2026.114705_bib0100","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2294","article-title":"HR-Depth: high resolution self-supervised monocular depth estimation","volume":"vol. 35","author":"Lyu","year":"2021"},{"key":"10.1016\/j.asoc.2026.114705_bib0105","doi-asserted-by":"crossref","first-page":"13706","DOI":"10.1109\/TITS.2024.3402655","article-title":"Lam-Depth: laplace-attention module-based self-supervised monocular depth estimation","volume":"25","author":"Wei","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0110","doi-asserted-by":"crossref","first-page":"2548","DOI":"10.1007\/s11263-021-01484-6","article-title":"Unsupervised scale-consistent depth learning from video","volume":"129","author":"Bian","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.asoc.2026.114705_bib0115","doi-asserted-by":"crossref","first-page":"9802","DOI":"10.1109\/TPAMI.2021.3136220","article-title":"Auto-rectify network for unsupervised indoor depth estimation","volume":"44","author":"Bian","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.114705_bib0120","doi-asserted-by":"crossref","first-page":"5585","DOI":"10.1109\/TITS.2025.3529999","article-title":"Eds-Depth: enhancing self-supervised monocular depth estimation in dynamic scenes","volume":"26","author":"Yu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0125","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"146","article-title":"High-precision self-supervised monocular depth estimation with rich-resource prior","author":"Han","year":"2024"},{"key":"10.1016\/j.asoc.2026.114705_bib0130","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5555","article-title":"Recurrent neural network for (un-) supervised learning of monocular video visual odometry and depth","author":"Wang","year":"2019"},{"key":"10.1016\/j.asoc.2026.114705_bib0135","doi-asserted-by":"crossref","first-page":"6813","DOI":"10.1109\/LRA.2020.3017478","article-title":"Don\u2019t forget the past: recurrent depth estimation from monocular video","volume":"5","author":"Patil","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.asoc.2026.114705_bib0140","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8606","article-title":"IterMVS: iterative probability estimation for efficient multi-view stereo","author":"Wang","year":"2022"},{"key":"10.1016\/j.asoc.2026.114705_bib0145","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2689","article-title":"Crafting monocular cues and velocity guidance for self-supervised multi-frame depth learning","volume":"vol. 37","author":"Wang","year":"2023"},{"key":"10.1016\/j.asoc.2026.114705_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"726","article-title":"Dualrefine: self-supervised depth and pose estimation through iterative epipolar sampling and refinement toward equilibrium","author":"Bangunharcana","year":"2023"},{"key":"10.1016\/j.asoc.2026.114705_bib0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102363","article-title":"Self-supervised multi-frame depth estimation with visual-inertial pose transformer and monocular guidance","volume":"108","author":"Wang","year":"2024","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.asoc.2026.114705_bib0160","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1109\/TCSVT.2023.3284479","article-title":"Iterdepth: iterative residual refinement for outdoor self-supervised multi-frame monocular depth estimation","volume":"34","author":"Feng","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.114705_bib0165","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"90","article-title":"Mono-vifi: a unified learning framework for self-supervised single and multi-frame monocular depth estimation","author":"Liu","year":"2024"},{"key":"10.1016\/j.asoc.2026.114705_bib0170","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"201","article-title":"Prodepth: boosting self-supervised multi-frame monocular depth with probabilistic fusion","author":"Woo","year":"2024"},{"key":"10.1016\/j.asoc.2026.114705_bib0175","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"652","article-title":"Uncertainty estimates and multi-hypotheses networks for optical flow","author":"Ilg","year":"2018"},{"key":"10.1016\/j.asoc.2026.114705_bib0180","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"613","article-title":"Gradient-based uncertainty for monocular depth estimation","author":"Hornauer","year":"2022"},{"key":"10.1016\/j.asoc.2026.114705_bib0185","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"43","article-title":"Variational depth networks: uncertainty-aware monocular self-supervised depth estimation","author":"Dikov","year":"2022"},{"key":"10.1016\/j.asoc.2026.114705_bib0190","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume":"30","author":"Kendall","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0195","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume":"32","author":"Ovadia","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0200","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1007\/s11390-023-3088-y","article-title":"Self-supervised monocular depth estimation by digging into uncertainty quantification","volume":"38","author":"Li","year":"2023","journal-title":"J. Comput. Sci. Technol."},{"key":"10.1016\/j.asoc.2026.114705_bib0205","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.asoc.2026.114705_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10138","article-title":"Adaptive fusion of single-view and multi-view depth for autonomous driving","author":"Cheng","year":"2024"},{"key":"10.1016\/j.asoc.2026.114705_bib0215","doi-asserted-by":"crossref","first-page":"6547","DOI":"10.1109\/LRA.2023.3309134","article-title":"Exploring the mutual influence between self-supervised single-frame and multi-frame depth estimation","volume":"8","author":"Xiang","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.asoc.2026.114705_bib0220","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume":"32","author":"Bian","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? The kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.asoc.2026.114705_bib0230","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3213","article-title":"The cityscapes dataset for semantic urban scene understanding","author":"Cordts","year":"2016"},{"key":"10.1016\/j.asoc.2026.114705_bib0235","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"Silberman","year":"2012"},{"key":"10.1016\/j.asoc.2026.114705_bib0240","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2650","article-title":"Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture","author":"Eigen","year":"2015"},{"key":"10.1016\/j.asoc.2026.114705_bib0245","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.asoc.2026.114705_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112552","article-title":"Lda-mono: a lightweight dual aggregation network for self-supervised monocular depth estimation","volume":"304","author":"Zhao","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0255","doi-asserted-by":"crossref","first-page":"20536","DOI":"10.1109\/TITS.2025.3581577","article-title":"Self-supervised monocular depth estimation with progressive enhancement of local-to-global visual perception","volume":"26","author":"Song","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.114705_bib0260","doi-asserted-by":"crossref","first-page":"6704","DOI":"10.1109\/LRA.2025.3568337","article-title":"Manydepth2: motion-aware self-supervised monocular depth estimation in dynamic scenes","volume":"10","author":"Zhou","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.asoc.2026.114705_bib0265","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"565","article-title":"Ra-Depth: resolution adaptive self-supervised monocular depth estimation","author":"He","year":"2022"},{"key":"10.1016\/j.asoc.2026.114705_bib0270","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12787","article-title":"Monoindoor: towards good practice of self-supervised monocular depth estimation for indoor environments","author":"Ji","year":"2021"},{"key":"10.1016\/j.asoc.2026.114705_bib0275","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1109\/TCSVT.2022.3207105","article-title":"Monoindoor++: towards better practice of self-supervised monocular depth estimation for indoor environments","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.114705_bib0280","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"16209","article-title":"Gasmono: geometry-aided self-supervised monocular depth estimation for indoor scenes","author":"Zhao","year":"2023"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626001535?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626001535?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T23:24:24Z","timestamp":1779233064000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626001535"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":56,"alternative-id":["S1568494626001535"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.114705","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MFU-Depth: Modeling and fusing uncertainty for self-supervised multi-frame monocular depth estimation","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.114705","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114705"}}