{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:23:17Z","timestamp":1758846197746,"version":"3.44.0"},"reference-count":36,"publisher":"Optica Publishing Group","issue":"28","license":[{"start":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T00:00:00Z","timestamp":1758758400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/doi.org\/10.1364\/OA_License_v2#VOR"},{"start":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T00:00:00Z","timestamp":1758758400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/opg.optica.org\/policies\/opg-tdm-policy.json"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62275229"],"award-info":[{"award-number":["62275229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["opg.optica.org"],"crossmark-restriction":false},"short-container-title":["Appl. Opt."],"published-print":{"date-parts":[[2025,10,1]]},"abstract":"<jats:p>Unmanned aerial vehicles (UAVs) have been increasingly employed in a wide range of applications, including environmental monitoring, precision agriculture, and infrastructure inspection. However, image blur frequently occurs in UAV-acquired imagery, compromising visual quality and adversely affecting high-level vision tasks such as object detection, classification, and 3D reconstruction. This study addresses image blur originating from camera-related factors. Without access to the optical design specifications, we estimate the point spread function (PSF) across various fields of view through camera calibration. These PSFs are subsequently utilized to synthesize a blurred dataset for training a deep neural network, which is then employed to restore sharpness in real-world captured images. Additionally, we assess the performance of several existing deblurring techniques and compare them with our PSF-driven approach. Experimental results indicate that our method outperforms competing techniques in real image deblurring scenarios.<\/jats:p>","DOI":"10.1364\/ao.573177","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:00:13Z","timestamp":1757350813000},"page":"8380","update-policy":"https:\/\/doi.org\/10.1364\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-world UAV image deblurring by PSF calibration"],"prefix":"10.1364","volume":"64","author":[{"given":"Gongfu","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Menghao","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihai","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2759-9784","authenticated-orcid":true,"given":"Yueting","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"285","published-online":{"date-parts":[[2025,9,25]]},"reference":[{"year":"2017","author":"Kupyn","key":"ao-64-28-8380-R1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.07064"},{"key":"ao-64-28-8380-R2","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/TBIOM.2018.2890577","volume":"1","author":"Lu","year":"2019","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"ao-64-28-8380-R3","first-page":"108.1","article-title":"Incremental dictionary learning for unsupervised domain adaptation","volume-title":"British Machine Vision Conference","author":"Lu","year":"2015"},{"key":"ao-64-28-8380-R4","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1109\/VR.2019.8797745","article-title":"A neural motion deblurring approach to restore rich textures for visual slam","volume-title":"IEEE Conference on Virtual Reality and 3D User Interfaces (VR)","author":"Jin","year":"2019"},{"key":"ao-64-28-8380-R5","doi-asserted-by":"publisher","first-page":"29721","DOI":"10.1364\/OE.524571","volume":"32","author":"Qin","year":"2024","journal-title":"Opt. Express"},{"key":"ao-64-28-8380-R6","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1145\/1141911.1141956","volume":"25","author":"Fergus","year":"2006","journal-title":"ACM Trans. Graph."},{"key":"ao-64-28-8380-R7","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/83.661187","volume":"7","author":"Chan","year":"1998","journal-title":"IEEE Trans. Image Process."},{"key":"ao-64-28-8380-R8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1360612.1360672","volume":"27","author":"Shan","year":"2008","journal-title":"ACM Trans. Graph."},{"key":"ao-64-28-8380-R9","first-page":"1033","article-title":"Fast image deconvolution using hyper-Laplacian priors","volume-title":"Proceedings of the 23rd International Conference on Neural Information Processing Systems","volume":"22","author":"Krishnan","year":"2009"},{"key":"ao-64-28-8380-R10","first-page":"1628","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Pan","year":"2016"},{"key":"ao-64-28-8380-R11","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1038\/s41592-025-02684-5","volume":"22","author":"Kohli","year":"2025","journal-title":"Nat. Methods"},{"key":"ao-64-28-8380-R12","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1364\/OPTICA.442438","volume":"9","author":"Yanny","year":"2022","journal-title":"Optica"},{"key":"ao-64-28-8380-R13","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1109\/TPAMI.2015.2481418","volume":"38","author":"Schuler","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ao-64-28-8380-R14","first-page":"3883","article-title":"Deep multi-scale convolutional neural network for dynamic scene deblurring","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Nah","year":"2017"},{"key":"ao-64-28-8380-R15","first-page":"5728","article-title":"Restormer: efficient transformer for high-resolution image restoration","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zamir","year":"2022"},{"key":"ao-64-28-8380-R16","first-page":"17683","article-title":"Uformer: a general u-shaped transformer for image restoration","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2022"},{"key":"ao-64-28-8380-R17","first-page":"74","article-title":"Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization","volume-title":"European Conference on Computer Vision","author":"Yang","year":"2024"},{"key":"ao-64-28-8380-R18","doi-asserted-by":"publisher","first-page":"4851","DOI":"10.1364\/OL.531253","volume":"49","author":"Wei","year":"2024","journal-title":"Opt. Lett."},{"key":"ao-64-28-8380-R19","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.jaerosci.2011.01.007","volume":"42","author":"Kim","year":"2011","journal-title":"J. Aerosol Sci."},{"key":"ao-64-28-8380-R20","first-page":"1314","article-title":"Real-world deep local motion deblurring","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Li","year":"2023"},{"key":"ao-64-28-8380-R21","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/978-3-642-33786-4_3","article-title":"Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database","volume-title":"Computer Vision\u2013ECCV 2012: 12th European Conference on Computer Vision, Proceedings, Part VII 12","author":"K\u00f6hler","year":"2012"},{"key":"ao-64-28-8380-R22","doi-asserted-by":"publisher","first-page":"657","DOI":"10.3390\/drones7110657","volume":"7","author":"Lee","year":"2023","journal-title":"Drones"},{"key":"ao-64-28-8380-R23","first-page":"1","article-title":"NTIRE 2019 challenge on video deblurring and super-resolution: dataset and study","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Nah","year":"2019"},{"volume-title":"Introduction to Fourier Optics","year":"2005","author":"Goodman","key":"ao-64-28-8380-R24"},{"key":"ao-64-28-8380-R25","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1145\/3474088","volume":"40","author":"Chen","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"ao-64-28-8380-R26","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/978-3-642-15549-9_13","article-title":"Single image deblurring using motion density functions","volume-title":"Computer Vision\u2013ECCV 2010: 11th European Conference on Computer Vision, Proceedings, Part I 11","author":"Gupta","year":"2010"},{"key":"ao-64-28-8380-R27","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1007\/s11263-011-0502-7","volume":"98","author":"Whyte","year":"2012","journal-title":"Int. J. Comput. Vis."},{"key":"ao-64-28-8380-R28","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/S0034-4257(01)00298-X","volume":"80","author":"Huang","year":"2002","journal-title":"Remote Sens. Environ."},{"key":"ao-64-28-8380-R29","first-page":"3226","article-title":"Can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark","volume-title":"IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","author":"Maggiori","year":"2017"},{"key":"ao-64-28-8380-R30","first-page":"4641","article-title":"Rethinking coarse-to-fine approach in single image deblurring","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Cho","year":"2021"},{"key":"ao-64-28-8380-R31","first-page":"1905","article-title":"Real-ESRGAN: training real-world blind super-resolution with pure synthetic data","volume-title":"International Conference on Computer Vision Workshops (ICCVW)","author":"Wang","year":"2021"},{"key":"ao-64-28-8380-R32","article-title":"Selective frequency network for image restoration","volume-title":"The Eleventh International Conference on Learning Representations","author":"Cui","year":"2023"},{"key":"ao-64-28-8380-R33","doi-asserted-by":"publisher","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ao-64-28-8380-R34","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"key":"ao-64-28-8380-R35","first-page":"1","article-title":"Blind image quality evaluation using perception based features","volume-title":"Twenty First National Conference on Communications (NCC)","author":"Venkatanath","year":"2015"},{"key":"ao-64-28-8380-R36","doi-asserted-by":"publisher","first-page":"2579","DOI":"10.1109\/TIP.2015.2426416","volume":"24","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Image Process."}],"container-title":["Applied Optics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/opg.optica.org\/viewmedia.cfm?URI=ao-64-28-8380&seq=0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T19:05:35Z","timestamp":1758827135000},"score":1,"resource":{"primary":{"URL":"https:\/\/opg.optica.org\/abstract.cfm?URI=ao-64-28-8380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,25]]},"references-count":36,"journal-issue":{"issue":"28","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1364\/ao.573177","relation":{},"ISSN":["1559-128X","2155-3165"],"issn-type":[{"type":"print","value":"1559-128X"},{"type":"electronic","value":"2155-3165"}],"subject":[],"published":{"date-parts":[[2025,9,25]]},"assertion":[{"value":"Optica Publishing Group","name":"publisher","label":"This article is maintained by"},{"value":"https:\/\/doi.org\/10.1364\/AO.573177","name":"articlelink","label":"Crossref DOI link to publisher maintained version"},{"value":"research-article","name":"content_type","label":"Article type"},{"value":"Screened by Similarity Check","name":"cross_check","label":"Similarity check"},{"value":"Yes","order":0,"name":"peer_reviewed","label":"Peer reviewed","group":{"name":"peer_review","label":"Peer review"}},{"value":"Single blind","order":1,"name":"review_process","label":"Review process","group":{"name":"peer_review","label":"Peer review"}},{"value":"10 July 2025","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"7 September 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"25 September 2025","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}},{"value":"\u00a9 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.","name":"copyright","label":"Copyright"}]}}