Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Advanced Photonics Nexus, Volume. 4, Issue 5, 056007(2025)

Learning from better simulation: creating highly realistic synthetic data for deep learning in scattering media

Bozhen Zhou1, Zhitao Hao1, Zhenbo Ren2,3、*, Edmund Y. Lam4, Jianshe Ma1, and Ping Su1、*
Author Affiliations
  • 1Tsinghua University, Tsinghua Shenzhen International Graduate School, Shenzhen, China
  • 2Northwestern Polytechnical University, School of Physical Science and Technology, Xi’an, China
  • 3Northwestern Polytechnical University, Shenzhen Research Institute, Shenzhen, China
  • 4The University of Hong Kong, Department of Electrical and Electronic Engineering, Hong Kong, China
    • show less
    Full TextGet PDF
    Figures&Tables (8)
    Equations (5)
    Suppl.&Mat.
    References (59)
    Tools
    Paper Information
    Topics
    References(59)

    [1] et alPolarimetric imaging through scattering media: a review. Front. Phys., 10, 815296(2022). https://doi.org/10.3389/fphy.2022.815296

    [2] et alPolarimetric image recovery method combining histogram stretching for underwater imaging. Sci. Rep., 8, 12430(2018). https://doi.org/10.1038/s41598-018-30566-8

    [3] Stimulated Raman scattering tomography enables label‐free volumetric deep tissue imaging. Laser Photonics Rev., 15, 2100069(2021). https://doi.org/10.1002/lpor.202100069

    [4] et alHigh speed color imaging through scattering media with a large field of view. Sci. Rep., 6, 32696(2016). https://doi.org/10.1038/srep32696

    [5] et alOptical coherence tomography. Science, 254, 1178-1181(1991). https://doi.org/10.1126/science.1957169

    [6] et alMultiplane quantitative phase imaging using a wavelength-multiplexed diffractive optical processor. Adv. Photonics, 6, 056003(2024). https://doi.org/10.1117/1.AP.6.5.056003

    [7] et alSolving inverse scattering problems in biological samples by quantitative phase imaging. Laser Photonics Rev., 10, 13-39(2016). https://doi.org/10.1002/lpor.201400467

    [8] et alTensorial tomographic Fourier ptychography with applications to muscle tissue imaging. Adv. Photonics, 6, 026004(2024). https://doi.org/10.1117/1.AP.6.2.026004

    [9] et alDeep optical imaging within complex scattering media. Nat. Rev. Phys., 2, 141-158(2020). https://doi.org/10.1038/s42254-019-0143-2

    [10] et alLearning-based lensless imaging through optically thick scattering media. Adv. Photonics, 1, 036002(2019). https://doi.org/10.1117/1.AP.1.3.036002

    [11] et alPhase imaging with an untrained neural network. Light Sci. Appl., 9, 77(2020). https://doi.org/10.1038/s41377-020-0302-3

    [12] et alReliable deep-learning-based phase imaging with uncertainty quantification. Optica, 6, 618-629(2019). https://doi.org/10.1364/OPTICA.6.000618

    [13] et alHolographic image reconstruction with phase recovery and autofocusing using recurrent neural networks. ACS Photonics, 8, 1763-1774(2021). https://doi.org/10.1021/acsphotonics.1c00337

    [14] et alDeep learning enables cross-modality super-resolution in fluorescence microscopy. Nat. Methods, 16, 103-110(2019). https://doi.org/10.1038/s41592-018-0239-0

    [15] et alDeep learning-based super-resolution in coherent imaging systems. Sci. Rep., 9, 3926(2019). https://doi.org/10.1038/s41598-019-40554-1

    [16] Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media. Optica, 5, 1181-1190(2018). https://doi.org/10.1364/OPTICA.5.001181

    [17] On the use of deep learning for computational imaging. Optica, 6, 921-943(2019). https://doi.org/10.1364/OPTICA.6.000921

    [18] et alOn the use of deep learning for phase recovery. Light Sci. Appl., 13, 4(2024). https://doi.org/10.1038/s41377-023-01340-x

    [19] et alMetasurface-based computational imaging: a review. Adv. Photonics, 6, 014002(2024). https://doi.org/10.1117/1.AP.6.1.014002

    [20] et alPhase recovery and holographic image reconstruction using deep learning in neural networks. Light Sci. Appl., 7, 17141-17141(2018). https://doi.org/10.1038/lsa.2017.141

    [21] Holographic 3D particle imaging with model-based deep network. IEEE Trans. Comput. Imaging, 7, 288-296(2021). https://doi.org/10.1109/TCI.2021.3063870

    [22] et alMachine learning holography for 3D particle field imaging. Opt. Express, 28, 2987-2999(2020). https://doi.org/10.1364/OE.379480

    [23] et alDense-U-net: dense encoder–decoder network for holographic imaging of 3D particle fields. Opt. Commun., 493, 126970(2021). https://doi.org/10.1016/j.optcom.2021.126970

    [24] et alShort U-net model with average pooling based on in-line digital holography for simultaneous restoration of multiple particles. Opt. Lasers Eng., 139, 106449(2021). https://doi.org/10.1016/j.optlaseng.2020.106449

    [25] et alCharacterization method for particle extraction from raw-reconstructed images using U-net. Front. Phys., 9, 816158(2022). https://doi.org/10.3389/fphy.2021.816158

    [26] et alNext-generation deep learning based on simulators and synthetic data. Trends Cognit. Sci., 26, 174-187(2022). https://doi.org/10.1016/j.tics.2021.11.008

    [27] . Synthetic Data for Deep Learning(2021).

    [28] et alTowards a multi-fidelity deep learning framework for a fast and realistic generation of ultrasonic multi-modal Total Focusing Method images in complex geometries. NDT & E Int., 139, 102906(2023). https://doi.org/10.1016/j.ndteint.2023.102906

    [29] et alGenerative domain-adapted adversarial auto-encoder model for enhanced ultrasonic imaging applications. NDT & E Int., 148, 103234(2024). https://doi.org/10.1016/j.ndteint.2024.103234

    [30] et alTracing multiple scattering trajectories for deep optical imaging in scattering media. Nat. Commun., 14, 6871(2023). https://doi.org/10.1038/s41467-023-42525-7

    [31] et alLarge-scale holographic particle 3D imaging with the beam propagation model. Opt. Express, 29, 17159-17172(2021). https://doi.org/10.1364/OE.424752

    [32] Adaptive 3D descattering with a dynamic synthesis network. Light Sci. Appl., 11, 42(2022). https://doi.org/10.1038/s41377-022-00730-x

    [33] et alDN-GAN: denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images. Biomed. Signal Process. Control, 55, 101632(2020). https://doi.org/10.1016/j.bspc.2019.101632

    [34] et alNon-invasive super-resolution imaging through dynamic scattering media. Nat. Commun., 12, 3150(2021). https://doi.org/10.1038/s41467-021-23421-4

    [35] Super-resolution two-photon fluorescence tomography through the phase-shifted optical beatings of Bessel beams for high-resolution deeper tissue 3D imaging. Laser Photonics Rev., 18, 2300634(2024). https://doi.org/10.1002/lpor.202300634

    [36] et alAccurate calculation of computer-generated holograms using angular-spectrum layer-oriented method. Opt. Express, 23, 25440-25449(2015). https://doi.org/10.1364/OE.23.025440

    [37] Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Trans. Image Process., 9, 889-896(2000). https://doi.org/10.1109/83.841534

    [38] et alImage quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process., 13, 600-612(2004). https://doi.org/10.1109/TIP.2003.819861

    [39] . Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence(1992).

    [40] et alA comparison of particle swarm optimization and the genetic algorithm(2012). https://doi.org/10.2514/6.2005-1897

    [41] U-Net: convolutional networks for biomedical image segmentation. Lect. Notes Comput. Sci., 9351, 234-241(2015). https://doi.org/10.1007/978-3-319-24574-4_28

    [42] et alMicroparticle characterization using digital holography. Chem. Eng. Sci., 65, 1037-1044(2010). https://doi.org/10.1016/j.ces.2009.09.057

    [43] et alTraining deep networks with synthetic data: bridging the reality gap by domain randomization, 969-977(2018). https://doi.org/10.1109/CVPRW.2018.00143

    [44] et alLimiting the incident NA for efficient wavefront shaping through thin anisotropic scattering media. Optica, 8, 428-437(2021). https://doi.org/10.1364/OPTICA.413174

    [45] Snapshot space–time holographic 3D particle tracking velocimetry. Laser Photonics Rev., 15, 2100008(2021). https://doi.org/10.1002/lpor.202100008

    [46] et alHolographic particle image velocimetry: from film to digital recording. Meas. Sci. Technol., 15, 673-685(2004). https://doi.org/10.1088/0957-0233/15/4/009

    [47] et alHigh accuracy label-free classification of single-cell kinetic states from holographic cytometry of human melanoma cells. Sci. Rep., 7, 11943(2017). https://doi.org/10.1038/s41598-017-12165-1

    [48] et alTomographic flow cytometry by digital holography. Light Sci. Appl., 6, e16241-e16241(2016). https://doi.org/10.1038/lsa.2016.241

    [49] et alA deep learning-enabled portable imaging flow cytometer for cost-effective, high-throughput, and label-free analysis of natural water samples. Light Sci. Appl., 7, 66(2018). https://doi.org/10.1038/s41377-018-0067-0

    [50] et alLabel-free detection of Giardia lamblia cysts using a deep learning-enabled portable imaging flow cytometer. Lab Chip, 20, 4404-4412(2020). https://doi.org/10.1039/D0LC00708K

    [51] et alIdentification of microplastics based on the fractal properties of their holographic fingerprint. ACS Photonics, 8, 2148-2157(2021). https://doi.org/10.1021/acsphotonics.1c00591

    [52] et alDetection of waterborne parasites using field-portable and cost-effective lensfree microscopy. Lab Chip, 10, 2419-2423(2010). https://doi.org/10.1039/c004829a

    [53] et alHigh-throughput microplastic assessment using polarization holographic imaging. Sci. Rep., 14, 2355(2024). https://doi.org/10.1038/s41598-024-52762-5

    [54] et alGenerative adversarial nets(2014).

    [55] A new microscopic principle. Nature, 161, 777-778(1948). https://doi.org/10.1038/161777a0

    [56] et alDigital holographic particle volume reconstruction using a deep neural network. Appl. Opt., 58, 1900-1906(2019). https://doi.org/10.1364/AO.58.001900

    [57] A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern., 9, 62-66(1979). https://doi.org/10.1109/TSMC.1979.4310076

    [58] et alAutomatic focusing in digital holography and its application to stretched holograms. Opt. Lett., 36, 1945-1947(2011). https://doi.org/10.1364/OL.36.001945

    [59] A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell., PAMI-8, 679-698(1986). https://doi.org/10.1109/TPAMI.1986.4767851

    Tools

    Get Citation

    Copy Citation Text

    Bozhen Zhou, Zhitao Hao, Zhenbo Ren, Edmund Y. Lam, Jianshe Ma, Ping Su, "Learning from better simulation: creating highly realistic synthetic data for deep learning in scattering media," Adv. Photon. Nexus 4, 056007 (2025)

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Research Articles

    Received: Mar. 27, 2025

    Accepted: Jul. 14, 2025

    Published Online: Aug. 27, 2025

    The Author Email: Zhenbo Ren (zbren@nwpu.edu.cn), Ping Su (su.ping@sz.tsinghua.edu.cn)

    DOI:10.1117/1.APN.4.5.056007

    CSTR:32397.14.1.APN.4.5.056007

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology