{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:07:01Z","timestamp":1785424021954,"version":"3.56.0"},"reference-count":52,"publisher":"Optica Publishing Group","issue":"10","license":[{"start":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:00:00Z","timestamp":1743033600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/doi.org\/10.1364\/OA_License_v2#VOR"},{"start":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:00:00Z","timestamp":1743033600000},"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\n\t\t\t\t\t\tChina","doi-asserted-by":"publisher","award":["62275017"],"award-info":[{"award-number":["62275017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Preliminary Study","award":["202303042"],"award-info":[{"award-number":["202303042"]}]}],"content-domain":{"domain":["opg.optica.org"],"crossmark-restriction":false},"short-container-title":["Appl. Opt."],"published-print":{"date-parts":[[2025,4,1]]},"abstract":"<jats:p>An all-in-focus\n\t\t\t\t\t( AIF) image has been employed\n\t\t\t\t\tbroadly in various fields such as microscopy imaging, medical imaging,\n\t\t\t\t\tand high-level vision tasks. Focus stacking is a key technology for\n\t\t\t\t\tmerging AIF images. Considerable efforts have been made to reconstruct\n\t\t\t\t\tAIF images accurately. However, little attention has been paid to\n\t\t\t\t\tcapturing focal stack images effectively. This paper proposes an\n\t\t\t\t\tadaptive image selection method for capturing focal stack images based\n\t\t\t\t\ton a low-level vision task-driven network and liquid lens. The\n\t\t\t\t\tproposed method can maintain the integral quality using the minimum\n\t\t\t\t\tnumber of focal stack images. The low-level vision task-driven network\n\t\t\t\t\ttermed FocalAIF-Net consists of a two-branch FocalNet and an auxiliary\n\t\t\t\t\tlow-level vision task AIFNet. The FocalNet can estimate the blur map\n\t\t\t\t\tand the focal map from a defocused image with its depth map. Various\n\t\t\t\t\tquantitative and qualitative evaluation results on three benchmark\n\t\t\t\t\tdatasets show that our FocalAIF-Net network achieves acceptable\n\t\t\t\t\tgeneralization performance. Additionally, we employ a liquid lens to\n\t\t\t\t\tzoom swiftly under the guidance of the proposed decision algorithm\n\t\t\t\t\tduring real-world experiments to verify the effectiveness of the\n\t\t\t\t\tproposed method. The results show that the focal stack acquired by our\n\t\t\t\t\tmethod has a strong capacity to merge a more accurate AIF image and\n\t\t\t\t\tconsume less running time compared to that achieved with a common\n\t\t\t\t\taverage interval by mechanical movement.<\/jats:p>","DOI":"10.1364\/ao.555601","type":"journal-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T10:00:22Z","timestamp":1741082422000},"page":"2653","update-policy":"https:\/\/doi.org\/10.1364\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive image selection method for focus stacking based on a low-level vision task-driven network and liquid lens"],"prefix":"10.1364","volume":"64","author":[{"given":"Jiale","family":"Wei","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01skt4w74","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Wang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01skt4w74","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Hao","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01skt4w74","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Changchun University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4348-3713","authenticated-orcid":true,"given":"Mengyao","family":"Liu","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01skt4w74","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1702-7122","authenticated-orcid":true,"given":"Yang","family":"Cheng","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01skt4w74","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Yangtze Delta Region Academy of Beijing Institute of Technology"},{"name":"National Key Laboratory on Near-Surface Detection"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"285","published-online":{"date-parts":[[2025,3,27]]},"reference":[{"key":"ao-64-10-2653-R1","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/TPAMI.2010.66","volume":"33","author":"Kuthirummal","year":"2010","journal-title":"IEEE Trans. Pattern Anal.\n\t\t\t\t\tMach. Intell."},{"key":"ao-64-10-2653-R2","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.inffus.2014.05.004","volume":"23","author":"Liu","year":"2015","journal-title":"Inform. Fusion"},{"key":"ao-64-10-2653-R3","first-page":"1071","article-title":"Focus on defocus:\n\t\t\t\t\tbridging the synthetic to real domain gap for depth\n\t\t\t\t\testimation","volume-title":"Proceedings of the IEEE\n\t\t\t\t\tConference on Computer Vision and Pattern Recognition","author":"Maximov","year":"2020"},{"key":"ao-64-10-2653-R4","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41377-023-01204-4","volume":"12","author":"Chen","year":"2023","journal-title":"Light-Sci. Appl."},{"key":"ao-64-10-2653-R5","doi-asserted-by":"publisher","first-page":"105277","DOI":"10.1016\/j.imavis.2024.105277","volume":"151","author":"Fang","year":"2024","journal-title":"Image Vision\n\t\t\t\t\tComput."},{"key":"ao-64-10-2653-R6","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/s13042-023-01927-1","volume":"15","author":"Ni","year":"2024","journal-title":"Int. J. Mach. Learn.\n\t\t\t\t\tCyb."},{"key":"ao-64-10-2653-R7","doi-asserted-by":"publisher","first-page":"103251","DOI":"10.1016\/j.cviu.2021.103251","volume":"210","author":"Chatterjee","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"ao-64-10-2653-R8","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.patrec.2023.03.009","volume":"168","author":"Mahaur","year":"2023","journal-title":"Pattern Recogn. Lett."},{"key":"ao-64-10-2653-R9","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.3390\/electronics12102323","volume":"12","author":"Lou","year":"2023","journal-title":"Electronics"},{"key":"ao-64-10-2653-R10","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1109\/ICCV.2009.5459269","article-title":"Time-constrained\n\t\t\t\t\tphotography","volume-title":"2009 IEEE 12th\n\t\t\t\t\tInternational Conference on Computer Vision","author":"Hasinoff","year":"2009"},{"key":"ao-64-10-2653-R11","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/WACV.2011.5711547","article-title":"Generalized autofocus","volume-title":"2011 IEEE Workshop on Applications of Computer Vision\n\t\t\t\t\t(WACV)","author":"Vaquero","year":"2011"},{"key":"ao-64-10-2653-R12","first-page":"2761","article-title":"Improved image selection for focus stacking in\n\t\t\t\t\tdigital photography","volume-title":"Proceedings of\n\t\t\t\t\tInternational Conference on Image Processing","author":"Choi","year":"2017"},{"key":"ao-64-10-2653-R13","first-page":"1887","article-title":"Scene-adaptive image acquisition for focus\n\t\t\t\t\tstacking","volume-title":"Proceedings of\n\t\t\t\t\tInternational Conference on Image Processing","author":"Li","year":"2018"},{"key":"ao-64-10-2653-R14","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1017\/S1551929515000577","volume":"23","author":"Clark","year":"2015","journal-title":"Microsc. Today"},{"key":"ao-64-10-2653-R15","doi-asserted-by":"publisher","first-page":"40024","DOI":"10.1364\/OE.413523","volume":"28","author":"Wu","year":"2020","journal-title":"Opt.\n\t\t\t\t\tExpress"},{"key":"ao-64-10-2653-R16","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1145\/965161.806818","volume":"15","author":"Potmesil","year":"1981","journal-title":"ACM T. Graphic."},{"key":"ao-64-10-2653-R17","first-page":"9140","article-title":"Fully self-supervised depth estimation from\n\t\t\t\t\tdefocus clue","volume-title":"Proceedings of the\n\t\t\t\t\tIEEE Conference on Computer Vision and Pattern Recognition","author":"Si","year":"2023"},{"key":"ao-64-10-2653-R18","first-page":"12222","article-title":"Deep\n\t\t\t\t\tdefocus map estimation using domain\n\t\t\t\t\tadaptation","volume-title":"Proceedings of the IEEE\n\t\t\t\t\tConference on Computer Vision and Pattern Recognition","author":"Lee","year":"2019"},{"key":"ao-64-10-2653-R19","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/29.45551","volume":"37","author":"Demoment","year":"1989","journal-title":"IEEE Trans. Acoustics Speech\n\t\t\t\t\tSignal Process."},{"key":"ao-64-10-2653-R20","article-title":"Pytorch: An imperative style, high-performance\n\t\t\t\t\tdeep learning library","volume-title":"Proceedings\n\t\t\t\t\tof the Advances in Neural Information Processing","volume":"32","author":"Paszke","year":"2019"},{"key":"ao-64-10-2653-R21","doi-asserted-by":"publisher","author":"Kingma","year":"2014","DOI":"10.48550\/arXiv.1412.6980"},{"key":"ao-64-10-2653-R22","article-title":"SGDR: stochastic\n\t\t\t\t\tgradient descent with warm restarts","volume-title":"Proceedings of the International Conference on Learning\n\t\t\t\t\tRepresentations","author":"Loshchilov","year":"2016"},{"key":"ao-64-10-2653-R23","first-page":"746","article-title":"Indoor segmentation and support inference from\n\t\t\t\t\tRGBD images","volume-title":"Proceedings of the\n\t\t\t\t\tEuropean Conference on Computer Vision","volume":"5","author":"Silberman","year":"2012"},{"key":"ao-64-10-2653-R24","first-page":"9043","article-title":"Metric3D: towards zero-shot metric 3d\n\t\t\t\t\tprediction from a single image","volume-title":"Proceedings of the IEEE Conference on Computer Vision and\n\t\t\t\t\tPattern Recognition","author":"Yin","year":"2023"},{"key":"ao-64-10-2653-R25","doi-asserted-by":"publisher","first-page":"5602","DOI":"10.1364\/AO.523864","volume":"63","author":"Cheng","year":"2024","journal-title":"Appl.\n\t\t\t\t\tOpt."},{"key":"ao-64-10-2653-R26","first-page":"1597","article-title":"Frequency-tuned salient region\n\t\t\t\t\tdetection","volume-title":"Proceedings of the IEEE\n\t\t\t\t\tConference on Computer Vision and Pattern Recognition","author":"Achanta","year":"2009"},{"key":"ao-64-10-2653-R27","first-page":"4548","article-title":"Structure-measure: a new way to evaluate\n\t\t\t\t\tforeground maps","volume-title":"Proceedings of the\n\t\t\t\t\tIEEE Conference on Computer Vision","author":"Fan","year":"2017"},{"key":"ao-64-10-2653-R28","doi-asserted-by":"publisher","author":"Fan","year":"2018","DOI":"10.48550\/arXiv.1805.10421"},{"key":"ao-64-10-2653-R29","doi-asserted-by":"publisher","author":"Bhat","year":"2023","DOI":"10.48550\/arXiv.2302.12288"},{"key":"ao-64-10-2653-R30","first-page":"2965","article-title":"Discriminative blur\n\t\t\t\t\tdetection features","volume-title":"Proceedings of\n\t\t\t\t\tthe IEEE Conference on Computer Vision and Pattern\n\t\t\t\t\tRecognition","author":"Shi","year":"2014"},{"key":"ao-64-10-2653-R31","first-page":"3080","article-title":"Defocus blur detection via multi-stream\n\t\t\t\t\tbottom-top-bottom fully convolutional network","volume-title":"Proceedings of the IEEE Conference on Computer Vision and\n\t\t\t\t\tPattern Recognition","author":"Zhao","year":"2018"},{"key":"ao-64-10-2653-R32","first-page":"2512","article-title":"Analyzing\n\t\t\t\t\tspatially-varying blur","volume-title":"Proceedings\n\t\t\t\t\tof the IEEE Conference on Computer Vision and Pattern\n\t\t\t\t\tRecognition","author":"Chakrabarti","year":"2010"},{"key":"ao-64-10-2653-R33","doi-asserted-by":"publisher","first-page":"2220","DOI":"10.1109\/TCYB.2015.2472478","volume":"46","author":"Pang","year":"2015","journal-title":"IEEE Trans.\n\t\t\t\t\tCybern."},{"key":"ao-64-10-2653-R34","first-page":"657","article-title":"Just noticeable defocus\n\t\t\t\t\tblur detection and estimation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and\n\t\t\t\t\tPattern Recognition","author":"Shi","year":"2015"},{"key":"ao-64-10-2653-R35","first-page":"1736","article-title":"A\n\t\t\t\t\tunified approach of multi-scale deep and hand-crafted features for\n\t\t\t\t\tdefocus estimation","volume-title":"Proceedings of\n\t\t\t\t\tthe IEEE Conference on Computer Vision and Pattern\n\t\t\t\t\tRecognition","author":"Park","year":"2017"},{"key":"ao-64-10-2653-R36","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1109\/TIP.2016.2528042","volume":"25","author":"Xin","year":"2016","journal-title":"IEEE Trans. Image\n\t\t\t\t\tProcess."},{"key":"ao-64-10-2653-R37","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1145\/2072298.2072024","article-title":"Blurred image region\n\t\t\t\t\tdetection and classification","volume-title":"Proceedings of the 19th ACM International Conference on\n\t\t\t\t\tMultimedia","author":"Su","year":"2011"},{"key":"ao-64-10-2653-R38","first-page":"5800","article-title":"Spatially-varying blur\n\t\t\t\t\tdetection based on multiscale fused and sorted transform coefficients\n\t\t\t\t\tof gradient magnitudes","volume-title":"Proceedings\n\t\t\t\t\tof the IEEE Conference on Computer Vision and Pattern\n\t\t\t\t\tRecognition","author":"Golestaneh","year":"2017"},{"key":"ao-64-10-2653-R39","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1109\/LSP.2016.2611608","volume":"23","author":"Tang","year":"2016","journal-title":"IEEE Signal Process\n\t\t\t\t\tLett."},{"key":"ao-64-10-2653-R40","doi-asserted-by":"publisher","first-page":"5155","DOI":"10.1109\/TIP.2018.2847421","volume":"27","author":"Ma","year":"2018","journal-title":"IEEE Trans. Image\n\t\t\t\t\tProcess."},{"key":"ao-64-10-2653-R41","first-page":"569","article-title":"United defocus blur detection and deblurring\n\t\t\t\t\tvia adversarial promoting learning","volume-title":"European Conference on Computer Vision","author":"Zhao","year":"2022"},{"key":"ao-64-10-2653-R42","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1109\/TPAMI.2020.3014629","volume":"44","author":"Tang","year":"2020","journal-title":"IEEE Trans. Pattern Anal.\n\t\t\t\t\tMach. Intell."},{"key":"ao-64-10-2653-R43","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/TMM.2020.2985541","volume":"23","author":"Tang","year":"2020","journal-title":"IEEE Trans.\n\t\t\t\t\tMultimedia"},{"key":"ao-64-10-2653-R44","first-page":"6933","article-title":"Self-generated defocus\n\t\t\t\t\tblur detection via dual adversarial\n\t\t\t\t\tdiscriminators","volume-title":"Proceedings of the\n\t\t\t\t\tIEEE Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2021"},{"key":"ao-64-10-2653-R45","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1109\/TIP.2023.3240856","volume":"32","author":"Li","year":"2023","journal-title":"IEEE Trans. Image\n\t\t\t\t\tProcess."},{"key":"ao-64-10-2653-R46","first-page":"8905","article-title":"Enhancing diversity of defocus blur detectors\n\t\t\t\t\tvia cross-ensemble network","volume-title":"Proceedings of the IEEE Conference on Computer Vision and\n\t\t\t\t\tPattern Recognition","author":"Zhao","year":"2019"},{"key":"ao-64-10-2653-R47","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1109\/TIP.2019.2942505","volume":"29","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ao-64-10-2653-R48","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TCI.2024.3354427","volume":"10","author":"Li","year":"2024","journal-title":"IEEE Trans. Comput.\n\t\t\t\t\tImaging"},{"key":"ao-64-10-2653-R49","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/978-3-319-10578-9_7","article-title":"RGBD\n\t\t\t\t\tsalient object detection: a benchmark and\n\t\t\t\t\talgorithms","volume-title":"Computer\n\t\t\t\t\tVision\u2013ECCV 2014: 13th European Conference","volume":"3","author":"Peng","year":"2014"},{"key":"ao-64-10-2653-R50","first-page":"1115","article-title":"Depth saliency based on anisotropic\n\t\t\t\t\tcenter-surround difference","volume-title":"Proceedings of International Conference on Image\n\t\t\t\t\tProcessing","author":"Ju","year":"2014"},{"key":"ao-64-10-2653-R51","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","volume":"54","author":"Zhang","year":"2020","journal-title":"Inform. Fusion"},{"key":"ao-64-10-2653-R52","doi-asserted-by":"publisher","first-page":"3","DOI":"10.11834\/jig.220422","volume":"28","author":"Tang","year":"2023","journal-title":"J. Image Graph."}],"container-title":["Applied Optics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/opg.optica.org\/viewmedia.cfm?URI=ao-64-10-2653&seq=0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T10:17:47Z","timestamp":1743416267000},"score":1,"resource":{"primary":{"URL":"https:\/\/opg.optica.org\/abstract.cfm?URI=ao-64-10-2653"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,27]]},"references-count":52,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1364\/ao.555601","relation":{},"ISSN":["1559-128X","2155-3165"],"issn-type":[{"value":"1559-128X","type":"print"},{"value":"2155-3165","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,27]]},"assertion":[{"value":"Optica Publishing Group","name":"publisher","label":"This article is maintained by"},{"value":"https:\/\/doi.org\/10.1364\/AO.555601","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":"14 January 2025","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"4 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"27 March 2025","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}},{"value":"\u00a9 2025 Optica Publishing Group. All rights,\n\t\t\t\t\tincluding for text and data mining (TDM), Artificial Intelligence (AI)\n\t\t\t\t\ttraining, and similar technologies, are\n\t\t\t\t\treserved.","name":"copyright","label":"Copyright"}]}}