Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in ...Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in speckle analysis,existing approaches are hindered by their dependence on large,labeled datasets—a significant bottleneck in many real-world applications.Here,we introduce speckle unsupervised recognition and evaluation(SURE),a groundbreaking unsupervised learning strategy for speckle recognition that eliminates the need for labeled training data.SURE's distinctive feature lies in its ability to extract invariant features through advanced clustering algorithms to enable direct classification of high-level information from speckle patterns without prior knowledge.We demonstrate the transformative potential of this approach in two key applications:(1)a noninvasive glucose monitoring system that accurately tracks glucose concentrations over time without extensive calibration and(2)a high-throughput communication system using multimode fibers,achieving improved performance in dynamic environments.In addition,we showcase SURE's unprecedented capability to classify objects hidden behind obstacles using scattered light,further broadening its scope.This versatile approach opens new frontiers in biomedical diagnostics,quantum network decoupling,and remote sensing,unlocking a transformative new paradigm for extracting information from seemingly random optical patterns.展开更多
In complex media scattering,multiple scattering severely degrades the optical wavefront and results in blurred images,while the spectral distortion caused by the scattering effect leads to severe color distortion.Achi...In complex media scattering,multiple scattering severely degrades the optical wavefront and results in blurred images,while the spectral distortion caused by the scattering effect leads to severe color distortion.Achieving color high-resolution imaging through scattering media remains a significant challenge.Here,we propose a broadband,polarization-based method for color high-resolution imaging through scattering media.This approach enables high-resolution reconstruction by effectively separating the speckle illumination pattern from the mixed-scattering field information,leveraging polarization common-mode characteristics.Concurrently,it incorporates chromatic balance compensation to correct spectral aliasing in the scattered light field,enabling color high-resolution imaging through complex scattering media.To further optimize color distortion caused by scattering,a compensation strategy combining color constancy and white balance theory is adopted.Experimental results demonstrate that the proposed method significantly enhances both spatial resolution and color fidelity across various scattering conditions and target materials,showcasing strong adaptability and robustness.This approach provides an effective solution for achieving high-resolution color optical imaging in complex scattering environments.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.11934011,12074339,62075194,U21A6006,62202418,and U21B2004)the National Key Research and Development Program of China(Grant Nos.2019YFA0308100,2023YFB2806000,and 2022YFA1204700)+4 种基金the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB28000000)the Leading Innovation and Entrepreneurship Team in Zhejiang Province(Grant No.2020R01001)the Open Program of the State Key Laboratory of Advanced Optical Communication Systems and Networks at Shanghai Jiao Tong University(Grant No.2023GZKF024)the Fundamental Research Funds for the Central Universities,the Information Technology Center and State Key Lab of CAD&CG at the Zhejiang University,the Zhejiang Provincial Key Laboratory of Information Processing,Communication and Networking(IPCAN)the National Institutes of Health(NIH)(Grant Nos.R01GM127696,R01GM152633,R21GM142107,and R21CA269099)。
文摘Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in speckle analysis,existing approaches are hindered by their dependence on large,labeled datasets—a significant bottleneck in many real-world applications.Here,we introduce speckle unsupervised recognition and evaluation(SURE),a groundbreaking unsupervised learning strategy for speckle recognition that eliminates the need for labeled training data.SURE's distinctive feature lies in its ability to extract invariant features through advanced clustering algorithms to enable direct classification of high-level information from speckle patterns without prior knowledge.We demonstrate the transformative potential of this approach in two key applications:(1)a noninvasive glucose monitoring system that accurately tracks glucose concentrations over time without extensive calibration and(2)a high-throughput communication system using multimode fibers,achieving improved performance in dynamic environments.In addition,we showcase SURE's unprecedented capability to classify objects hidden behind obstacles using scattered light,further broadening its scope.This versatile approach opens new frontiers in biomedical diagnostics,quantum network decoupling,and remote sensing,unlocking a transformative new paradigm for extracting information from seemingly random optical patterns.
基金supported by the National Natural Science Foundation of China (Grant Nos. 62405231, 62405235, and 62575229)the National Key Laboratory of Space Target Awareness (Grant Nos. STA2024KGL0203, STA2024ZCA0203, and STA-24-04-05)+3 种基金the Beijing Key Laboratory of Advanced Optical Remote Sensing Technology (Grant No. AORS202405)the China Postdoctoral Science Foundation (Grant No. 2024M762527)the Shaanxi Province High-level Innovation and Entrepreneurship Talent Program (Grant No. H02439005)the Natural Science Foundation of Shaanxi (Grant Nos. S2024-JC-JCQN-60, S2025-JCQYTS-0107, and 2025JC-QYCX-05)。
文摘In complex media scattering,multiple scattering severely degrades the optical wavefront and results in blurred images,while the spectral distortion caused by the scattering effect leads to severe color distortion.Achieving color high-resolution imaging through scattering media remains a significant challenge.Here,we propose a broadband,polarization-based method for color high-resolution imaging through scattering media.This approach enables high-resolution reconstruction by effectively separating the speckle illumination pattern from the mixed-scattering field information,leveraging polarization common-mode characteristics.Concurrently,it incorporates chromatic balance compensation to correct spectral aliasing in the scattered light field,enabling color high-resolution imaging through complex scattering media.To further optimize color distortion caused by scattering,a compensation strategy combining color constancy and white balance theory is adopted.Experimental results demonstrate that the proposed method significantly enhances both spatial resolution and color fidelity across various scattering conditions and target materials,showcasing strong adaptability and robustness.This approach provides an effective solution for achieving high-resolution color optical imaging in complex scattering environments.
