{"id":346558,"date":"2026-06-04T14:54:09","date_gmt":"2026-06-04T14:54:09","guid":{"rendered":"https:\/\/www.newsbeep.com\/us-ca\/346558\/"},"modified":"2026-06-04T14:54:09","modified_gmt":"2026-06-04T14:54:09","slug":"uc-san-diego-team-pairs-ai-with-tiny-optical-device-to-correct-distorted-light-for-sharper-imaging","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us-ca\/346558\/","title":{"rendered":"UC San Diego team pairs AI with tiny optical device to correct distorted light for sharper imaging"},"content":{"rendered":"<p>                <a href=\"https:\/\/www.eurekalert.org\/multimedia\/1134299\" rel=\"nofollow noopener\" target=\"_blank\"><\/p>\n<p>                    <img decoding=\"async\" src=\"https:\/\/www.newsbeep.com\/us-ca\/wp-content\/uploads\/2026\/06\/Public.jpeg\" alt=\"Electron microscope images of AI-designed metasurface\"\/><\/p>\n<p>                <\/a><\/p>\n<p>image:\u00a0<\/p>\n<p>Electron microscope images show the AI-designed metasurface of the device fabricated in the UC San Diego Qualcomm Institute Nano3 facility. The left panel shows the array of titanium dioxide nanopillars on a glass substrate, while the zoomed-in image on the right reveals the tiny elliptical nanopillars that make up the metasurface.<\/p>\n<p>                  <a href=\"https:\/\/www.eurekalert.org\/multimedia\/1134299\" rel=\"nofollow noopener\" target=\"_blank\">view more\u00a0<\/a><\/p>\n<p class=\"credit\">Credit: Image by Ndao lab, UC San Diego<\/p>\n<p>Blurry light from lens imperfections is a problem everywhere from microscopes to telescopes to smartphone cameras. Using a tiny yet carefully engineered optical element and artificial intelligence, University of California San Diego engineers have built a way to spot and correct those distortions from a single image \u2014 a step that could make advanced optical systems faster, smaller and easier to use.<\/p>\n<p>\u201cWe used a combination of fundamental physics, nanofabrication and machine learning to make hidden distortions easier to detect and correct,\u201d said senior author Abdoulaye Ndao, an electrical and computer engineering faculty member in the Jacobs School of Engineering and an affiliate of the Qualcomm Institute at UC San Diego.<\/p>\n<p>\u201cOur fast, robust solution is tiny and easy to integrate into different optical systems,\u201d he continued. \u201cThe weight is almost nothing, because the size of the sample can be one by one centimeter and half a millimeter thick.\u201d<\/p>\n<p>The work\u00a0\u2014\u00a0whose co-first authors were UC San Diego Electrical and Computer Engineering Ph.D. students Sina Moayed Baharlou (also of Boston University) and Muhammad Waleed Khalid \u2014 was published in Nature Communications on May 12, 2026.<\/p>\n<p>Scalable and Practical<\/p>\n<p>Most current methods for correcting small imperfections that can warp light and reduce image quality require several measurements, extra hardware or repeated calculations to figure out what went wrong. That can make systems bulkier, slower and harder to integrate into compact devices.<\/p>\n<p>To tackle this problem, the UC San Diego team paired an optical element designed with artificial intelligence (Figure 1) with an AI-powered analysis system. Together, they give each optical distortion a unique image signature, allowing a deep neural network, a machine learning model inspired by the human brain, to read distortions from a single image of the light pattern and tell the system how to correct them. Once the researchers determined the approach could work at one wavelength, they kept expanding the device\u2019s capabilities until it worked across multiple wavelengths, held up under noisy conditions and handled complicated beam shapes.<\/p>\n<p>And the team did not just simulate the work. Using UC San Diego Qualcomm Institute\u2019s Nano3 cleanroom facility to create the optical device and different surfaces, the researchers fabricated key optical components and tested the approach experimentally across a range of conditions.<\/p>\n<p>The authors note that the paper establishes a scalable and practical foundation for real-time aberration correction for next-generation optical and photonic systems. The approach (patent pending) could improve the optical hardware used in fields including biology, astronomy and precision manufacturing.<\/p>\n<p>In addition to Ndao, Baharlou and Khalid, the paper \u201c<a href=\"https:\/\/www.nature.com\/articles\/s41467-026-72364-1\" rel=\"nofollow noopener\" target=\"_blank\">An end-to-end hybrid deep-learning approach for single-shot wavefront sensing and correction<\/a>\u201d was authored by Guli Gulinihali, Jeongho Ha, Liyi Hsu and Yeshaiahu Fainman of UC San Diego (Electrical and Computer Engineering), Samantha C. Lewis of UC Berkeley, and Lei Tian and Alexander V. Sergienko of Boston University.<\/p>\n<p>                            Journal<\/p>\n<p>Nature Communications<\/p>\n<p>                            Method of Research<\/p>\n<p>Imaging analysis<\/p>\n<p>                            Subject of Research<\/p>\n<p>Not applicable<\/p>\n<p>                            Article Title<\/p>\n<p>An end-to-end hybrid deep-learning approach for single-shot wavefront sensing and correction<\/p>\n<p>                            Article Publication Date<\/p>\n<p>12-May-2026<\/p>\n<p>                            COI Statement<\/p>\n<p>The authors declare no competing interests.<\/p>\n<p>Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.<\/p>\n","protected":false},"excerpt":{"rendered":"image:\u00a0 Electron microscope images show the AI-designed metasurface of the device fabricated in the UC San Diego Qualcomm&hellip;\n","protected":false},"author":2,"featured_media":346559,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[28],"tags":[74,76,75],"class_list":["post-346558","post","type-post","status-publish","format-standard","has-post-thumbnail","category-san-diego","tag-san-diego","tag-san-diego-headlines","tag-san-diego-news"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/posts\/346558","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/comments?post=346558"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/posts\/346558\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/media\/346559"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/media?parent=346558"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/categories?post=346558"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us-ca\/wp-json\/wp\/v2\/tags?post=346558"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}