{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T09:29:47Z","timestamp":1780046987777,"version":"3.53.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116207","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:43:50Z","timestamp":1778777030000},"page":"116207","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["SCFP-Depth: Achieving robust self-supervised monocular depth estimation via static compensation and frequency-domain priors"],"prefix":"10.1016","volume":"346","author":[{"given":"Chaochao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116207_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LSENS.2024.3367956","article-title":"Object depth and size estimation using stereo-vision and integration with slam","author":"Hamad","year":"2024","journal-title":"IEEE Sensors Lett."},{"key":"10.1016\/j.knosys.2026.116207_b2","unstructured":"Markus Sch\u00f6n, Michael Buchholz, Klaus Dietmayer, Mgnet: Monocular geometric scene understanding for autonomous driving, in: International Conference on Computer Vision(ICCV), 2024, pp. 15804\u201315815."},{"key":"10.1016\/j.knosys.2026.116207_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2025.110375","article-title":"Hybrid robot navigation: integrating monocular depth estimation and visual odometry for efficient navigation on low-resource hardware","author":"Vashisht","year":"2025","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.knosys.2026.116207_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.109038","article-title":"Depth estimation from monocular endoscopy using simulation and image transfer approach","author":"Jeong","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.knosys.2026.116207_b5","series-title":"From big to small: multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019"},{"key":"10.1016\/j.knosys.2026.116207_b6","doi-asserted-by":"crossref","unstructured":"Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka, Adabins: Depth estimation using adaptive bins, in: Computer Vision and Pattern Recognition(CVPR), 2021, pp. 4009\u20134018.","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"10.1016\/j.knosys.2026.116207_b7","doi-asserted-by":"crossref","first-page":"4131","DOI":"10.1109\/TIP.2018.2836318","article-title":"Deep monocular depth estimation via integration of global and local predictions","author":"Kim","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116207_b8","doi-asserted-by":"crossref","unstructured":"Tinghui Zhou, Matthew Brown, Noah Snavely, David G. Lowe, Unsupervised learning of depth and ego-motion from video, in: Computer Vision and Pattern Recognition(CVPR), 2017, pp. 1851\u20131858.","DOI":"10.1109\/CVPR.2017.700"},{"key":"10.1016\/j.knosys.2026.116207_b9","doi-asserted-by":"crossref","unstructured":"Cl\u00e9ment Godard, Oisin Mac Aodha, Michael Firman, Gabriel J Brostow, Digging into self-supervised monocular depth estimation, in: International Conference on Computer Vision (ICCV), 2019, pp. 3828\u20133838.","DOI":"10.1109\/ICCV.2019.00393"},{"key":"10.1016\/j.knosys.2026.116207_b10","unstructured":"Vincent Casser, Soeren Pirk, Reza Mahjourian, Anelia Angelova, Unsupervised monocular depth and ego-motion learning with structure and semantics, in: Computer Vision and Pattern Recognition Workshops(CVPRW), 1994."},{"key":"10.1016\/j.knosys.2026.116207_b11","doi-asserted-by":"crossref","unstructured":"Zhichao Yin, Jianping Shi, Geonet: Unsupervised learning of dense depth, optical flow and camera pose, in: Computer Vision and Pattern Recognition(CVPR), 2018, pp. 1983\u20131992.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"10.1016\/j.knosys.2026.116207_b12","doi-asserted-by":"crossref","unstructured":"H. Jung, E. Park, S. Yoo, Fine-grained semantics-aware representation enhancement for self-supervised monocular depth estimation, in: International Conference on Computer Vision (ICCV), 2021, pp. 12622\u201312632.","DOI":"10.1109\/ICCV48922.2021.01241"},{"key":"10.1016\/j.knosys.2026.116207_b13","doi-asserted-by":"crossref","unstructured":"Ning Zhang, Francesco Nex, George Vosselman, Norman Kerle, Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation, in: Computer Vision and Pattern Recognition (CVPR), 2023, pp. 18537\u201318546.","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"10.1016\/j.knosys.2026.116207_b14","doi-asserted-by":"crossref","unstructured":"Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, Xianda Guo, Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia, Monovit: Self-supervised monocular depth estimation with a vision transformer, in: 2022 international conference on 3D vision (3DV), 2022, pp. 668\u2013678.","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"10.1016\/j.knosys.2026.116207_b15","doi-asserted-by":"crossref","unstructured":"Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, Michael Firman, The temporal opportunist: Self-supervised multi-frame monocular depth, in: Computer Vision and Pattern Recognition (CVPR), 2021, pp. 1164\u20131174.","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"10.1016\/j.knosys.2026.116207_b16","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence(AAAI)","first-page":"2294","article-title":"Hr-depth: high resolution self-supervised monocular depth estimation","volume":"35, no. (3)","author":"Lyu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116207_b17","doi-asserted-by":"crossref","unstructured":"Jaeho Moon, Juan Luis Gonzalez Bello, Byeongjun Kwon, Munchurl Kim, From-ground-to-objects: Coarse-to-fine self-supervised monocular depth estimation of dynamic objects with ground contact prior, in: Computer Vision and Pattern Recognition (CVPR), 2024, pp. 10519\u201310529.","DOI":"10.1109\/CVPR52733.2024.01001"},{"key":"10.1016\/j.knosys.2026.116207_b18","doi-asserted-by":"crossref","unstructured":"Ziyue Feng, Liang Yang, Longlong Jing, Haiyan Wang, YingLi Tian, Bing Li, Disentangling object motion and occlusion for unsupervised multi-frame monocular depth, in: European Conference on Computer Vision(ECCV), 2022, pp. 228\u2013244.","DOI":"10.1007\/978-3-031-19824-3_14"},{"key":"10.1016\/j.knosys.2026.116207_b19","series-title":"FlowDepth: decoupling optical flow for self-supervised monocular depth estimation","first-page":"559","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.116207_b20","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","author":"Zhou","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.knosys.2026.116207_b21","first-page":"2564","article-title":"Ds-depth: dynamic and static depth estimation via a fusion cost volume","author":"Miao","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116207_b22","series-title":"Causal-tune: mining causal factors from vision foundation models for domain generalized semantic segmentation","first-page":"4129","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116207_b23","series-title":"Spjfnet: self-mining prior-guided joint frequency enhancement for ultra-efficient dark image restoration","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116207_b24","doi-asserted-by":"crossref","unstructured":"Andreas Geiger, Philip Lenz, Raquel Urtasun, Are we ready for autonomous driving? the kitti vision benchmark suite, in: Computer Vision and Pattern Recognition(CVPR), 2012, pp. 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10.1016\/j.knosys.2026.116207_b25","doi-asserted-by":"crossref","unstructured":"Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele, The cityscapes dataset for semantic urban scene understanding, in: Computer Vision and Pattern Recognition(CVPR), 2016, pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"issue":"5","key":"10.1016\/j.knosys.2026.116207_b26","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","article-title":"Make3D: Learning 3D Scene Structure from a Single Still Image","volume":"31","author":"Saxena","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116207_b27","doi-asserted-by":"crossref","unstructured":"Yue Meng, Yongxi Lu, Aman Raj, Samuel Sunarjo, Rui Guo, Tara Javidi, Gaurav Bansal, Dinesh Bharadia, Signet: Semantic instance aided unsupervised 3d geometry perception, in: Computer Vision and Pattern Recognition(CVPR), 2019, pp. 9810\u20139820.","DOI":"10.1109\/CVPR.2019.01004"},{"key":"10.1016\/j.knosys.2026.116207_b28","doi-asserted-by":"crossref","unstructured":"Po-Yi Chen, Alexander H. Liu, Yen-Cheng Liu, Yu-Chiang Frank Wang, Towards scene understanding: Unsupervised monocular depth estimation with semantic-aware representation, in: Computer Vision and Pattern Recognition(CVPR), 2019, pp. 2624\u20132632.","DOI":"10.1109\/CVPR.2019.00273"},{"key":"10.1016\/j.knosys.2026.116207_b29","series-title":"Safenet: self-supervised monocular depth estimation with semantic-aware feature extraction","first-page":"41","author":"Choi","year":"2020"},{"key":"10.1016\/j.knosys.2026.116207_b30","doi-asserted-by":"crossref","unstructured":"Marvin Klingner, Jan-Aike Term\u00f6hlen, Jonas Mikolajczyk, Tim Fingscheidt, Self-supervised monocular depth estimation: Solving the dynamic object problem by semantic guidance, in: European Conference on Computer Vision(ECCV), 2020.","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"10.1016\/j.knosys.2026.116207_b31","doi-asserted-by":"crossref","unstructured":"Hoang Chuong Nguyen, Tianyu Wang, Jose M Alvarez, Miaomiao Liu, Mining supervision for dynamic regions in self-supervised monocular depth estimation, in: Computer Vision and Pattern Recognition(CVPR), 2024, pp. 10446\u201310455.","DOI":"10.1109\/CVPR52733.2024.00994"},{"key":"10.1016\/j.knosys.2026.116207_b32","series-title":"Swinfir: revisiting the swinir with fast fourier convolution and improved training for image super-resolution","first-page":"2","author":"Zhang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116207_b33","doi-asserted-by":"crossref","unstructured":"Xingyu Jiang, Xiuhui Zhang, Ning Gao, Yue Deng, When fast fourier transform meets transformer for image restoration, in: European Conference on Computer Vision, 2024, pp. 381\u2013402.","DOI":"10.1007\/978-3-031-72995-9_22"},{"key":"10.1016\/j.knosys.2026.116207_b34","first-page":"1","article-title":"FCMMA: fourier conditional mask based mixed attention method for hyperspectral anomaly detection","author":"Wang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.116207_b35","doi-asserted-by":"crossref","unstructured":"Micha\u00ebl Ramamonjisoa, Michael Firman, Jamie Watson, Vincent Lepetit, Daniyar Turmukhambetov, Single image depth prediction with wavelet decomposition, in: Computer Vision and Pattern Recognition(CVPR), 2021, pp. 11089\u201311098.","DOI":"10.1109\/CVPR46437.2021.01094"},{"key":"10.1016\/j.knosys.2026.116207_b36","doi-asserted-by":"crossref","unstructured":"Menglong Yang, Fangrui Wu, Wei Li, Waveletstereo: Learning wavelet coefficients of disparity map in stereo matching, in: Computer Vision and Pattern Recognition(CVPR), 2020, pp. 12885\u201312894.","DOI":"10.1109\/CVPR42600.2020.01290"},{"key":"10.1016\/j.knosys.2026.116207_b37","doi-asserted-by":"crossref","unstructured":"Zachary Teed, Jia Deng, Raft: Recurrent all-pairs field transforms for optical flow, in: European conference on computer vision(ECCV), 2020, pp. 402\u2013419.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"10.1016\/j.knosys.2026.116207_b38","doi-asserted-by":"crossref","unstructured":"Tongshun Zhang, Pingping Liu, Ming Zhao, Haotian Lv, Dmfourllie: Dual-stage and multi-branch fourier network for low-light image enhancement, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 7434\u20137443.","DOI":"10.1145\/3664647.3681083"},{"key":"10.1016\/j.knosys.2026.116207_b39","doi-asserted-by":"crossref","unstructured":"K.M. He, X.Y. Zhang, S.Q. Ren, J. Sun, Deep Residual Learning for Image Recognition, in: Computer Vision and Pattern Recognition(CVPR), 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.116207_b40","doi-asserted-by":"crossref","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, Imagenet: A large-scale hierarchical image database, in: Computer Vision and Pattern Recognition(CVPR), 2009, pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.knosys.2026.116207_b41","unstructured":"Youngwan Lee, Jonghee Kim, Jeffrey Willette, Sung Ju Hwang, Mpvit: Multi-path vision transformer for dense prediction, in: Computer Vision and Pattern Recognition (CVPR), 2022, pp. 7287\u20137296."},{"key":"10.1016\/j.knosys.2026.116207_b42","doi-asserted-by":"crossref","unstructured":"Chaoyang Wang, Jos\u00e9 Miguel Buenaposada, Rui Zhu, Simon Lucey, Learning depth from monocular videos using direct methods, in: Computer Vision and Pattern Recognition(CVPR), 2018, pp. 2022\u20132030.","DOI":"10.1109\/CVPR.2018.00216"},{"key":"10.1016\/j.knosys.2026.116207_b43","series-title":"Monoformer: towards generalization of self-supervised monocular depth estimation with transformers","author":"Bae","year":"2022"},{"key":"10.1016\/j.knosys.2026.116207_b44","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2023.3330054","article-title":"Edge devices friendly self-supervised monocular depth estimation via knowledge distillation","author":"Gao","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.knosys.2026.116207_b45","first-page":"3664","article-title":"MonoDiffusion: self-supervised monocular depth estimation using diffusion model","author":"Shao","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116207_b46","first-page":"5585","article-title":"Dual attention guidance network for self-supervised monocular depth estimation","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116207_b47","first-page":"1","article-title":"Er-depth: enhancing the robustness of self-supervised monocular depth estimation in challenging scenes","author":"Song","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.knosys.2026.116207_b48","doi-asserted-by":"crossref","unstructured":"Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao, Yao Zhao, Digging into contrastive learning for robust depth estimation with diffusion models, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 4129\u20134137.","DOI":"10.1145\/3664647.3681168"},{"key":"10.1016\/j.knosys.2026.116207_b49","unstructured":"Qiang Gao, Gang Peng, Zeyuan Chen, Bingchuan Yang, Digging into contrastive learning for robust depth estimation with diffusion models, in: International Conference on Neural Information Processing, 2024, pp. 153\u2013168."},{"key":"10.1016\/j.knosys.2026.116207_b50","doi-asserted-by":"crossref","unstructured":"Zhongkai Zhou, Xinnan Fan, Pengfei Shi, Yuanxue Xin, R-msfm: Recurrent multi-scale feature modulation for monocular depth estimating, in: international conference on computer vision, 2021, pp. 12777\u201312786.","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"10.1016\/j.knosys.2026.116207_b51","doi-asserted-by":"crossref","unstructured":"Mu He, Le Hui, Yikai Bian, Jian Ren, Jin Xie, Jian Yang, RA-depth: Resolution adaptive self-supervised monocular depth estimation, in: European Conference on Computer Vision (ECCV), 2022, pp. 565\u2013581.","DOI":"10.1007\/978-3-031-19812-0_33"},{"key":"10.1016\/j.knosys.2026.116207_b52","unstructured":"Seokju Lee, Francois Rameau, Fei Pan, In So Kweon, Attentive and contrastive learning for joint depth and motion field estimation, in: International Conference on Computer Vision(ICCV), 2021, pp. 4862\u20134871."},{"key":"10.1016\/j.knosys.2026.116207_b53","unstructured":"Hanhan Li, Ariel Gordon, Hang Zhao, Vincent Casser, Anelia Angelova, Unsupervised monocular depth learning in dynamic scenes, in: Conference on Robot Learning, 2021, pp. 1908\u20131917."},{"key":"10.1016\/j.knosys.2026.116207_b54","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8001","article-title":"Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos","volume":"33, no. (01)","author":"Casser","year":"2019"},{"key":"10.1016\/j.knosys.2026.116207_b55","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","author":"Yu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009330?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009330?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:12:31Z","timestamp":1780017151000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":55,"alternative-id":["S0950705126009330"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116207","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SCFP-Depth: Achieving robust self-supervised monocular depth estimation via static compensation and frequency-domain priors","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116207","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":"116207"}}