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

Laser & Optoelectronics Progress, Volume. 62, Issue 17, 1739010(2025)

Deep Learning-Driven Single-Pixel Imaging: Advances and Challenges (Invited)

Kai Song1,2,3, Hongrui Liu1,2,3, Yaoxing Bian1,2,3、*, Shijun Zhao1,2,3, Dong Wang1,2,3, and Liantuan Xiao1,2,3,4、**
Author Affiliations
  • 1College of Physics and Optoelectronics Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi , China
  • 2Key Laboratory of Advanced Transducers and Intelligent Control System, Ministry of Education and Shanxi Province, Taiyuan University of Technology, Taiyuan 030024, Shanxi , China
  • 3Shanxi Key Laboratory of Precision Measurement Physics, Taiyuan University of Technology, Taiyuan 030024, Shanxi ,China
  • 4State Key Laboratory of Quantum Optics Technologies and Devices, Shanxi University, Taiyuan 030006, Shanxi , China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (14)
    References (144)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Single-pixel imaging driven by deep learning[5, 38, 41-50]

    Fig. 1. Single-pixel imaging driven by deep learning[5, 38, 41-50]

    Download full size
    Two single-pixel imaging schemes. (a) Structural detection; (b) structural illumination

    Fig. 2. Two single-pixel imaging schemes. (a) Structural detection; (b) structural illumination

    Download full size
    Basic principle of neural network. (a) Basic structure of neural network; (b) supervised learning; (c) self-supervised learning

    Fig. 3. Basic principle of neural network. (a) Basic structure of neural network; (b) supervised learning; (c) self-supervised learning

    Download full size
    Common neural networks in single-pixel imaging. (a) Upsampled CNN[79]; (b) self-coded CNN[80]; (c) RNN[81]; (d) GAN[82]; (e) Transformer[83]; (f) diffusion model[84]

    Fig. 4. Common neural networks in single-pixel imaging. (a) Upsampled CNN[79]; (b) self-coded CNN[80]; (c) RNN[81]; (d) GAN[82]; (e) Transformer[83]; (f) diffusion model[84]

    Download full size
    Image denoising based on supervised learning. (a) Detailed process of image denoising based on supervised learning; (b) high quality ghost imaging based on supervised learning image denoising[85]; (c) hyperspectral imaging based on supervised learning image denoising[42]; (d) super-resolution imaging based on supervised learning image denoising[86]

    Fig. 5. Image denoising based on supervised learning. (a) Detailed process of image denoising based on supervised learning; (b) high quality ghost imaging based on supervised learning image denoising[85]; (c) hyperspectral imaging based on supervised learning image denoising[42]; (d) super-resolution imaging based on supervised learning image denoising[86]

    Download full size
    Image denoising based on unsupervised learning. (a) Detailed flow of image denoising based on unsupervised learning; (b) far-field super-resolution imaging based on unsupervised learning image denoising[43]; (c) unsupervised learning image denoising based on pre-training[5]

    Fig. 6. Image denoising based on unsupervised learning. (a) Detailed flow of image denoising based on unsupervised learning; (b) far-field super-resolution imaging based on unsupervised learning image denoising[43]; (c) unsupervised learning image denoising based on pre-training[5]

    Download full size
    Image reconstruction based on supervised learning. (a) Detailed process of image reconstruction based on supervised learning; (b) real-time imaging based on supervised learning image reconstruction[110]; (c) imaging through scattering media based on supervised learning image reconstruction[111]; (d) supervised learning image reconstruction based on simulated data[48]

    Fig. 7. Image reconstruction based on supervised learning. (a) Detailed process of image reconstruction based on supervised learning; (b) real-time imaging based on supervised learning image reconstruction[110]; (c) imaging through scattering media based on supervised learning image reconstruction[111]; (d) supervised learning image reconstruction based on simulated data[48]

    Download full size
    Image reconstruction based on unsupervised learning. (a) Detailed process of image reconstruction based on unsupervised learning; (b) unsupervised learning image reconstruction based on measurements mapping[38]; (c) unsupervised learning image reconstruction based on random noise mapping[45]

    Fig. 8. Image reconstruction based on unsupervised learning. (a) Detailed process of image reconstruction based on unsupervised learning; (b) unsupervised learning image reconstruction based on measurements mapping[38]; (c) unsupervised learning image reconstruction based on random noise mapping[45]

    Download full size
    Image-free sensing. (a) Detailed process of image-free sensing; (b) image-free target classification[122]; (c) image-free target segmentation[123]; (d) image-free target detection[124]

    Fig. 9. Image-free sensing. (a) Detailed process of image-free sensing; (b) image-free target classification[122]; (c) image-free target segmentation[123]; (d) image-free target detection[124]

    Download full size
    Performance improvement brought by neural networks

    Fig. 10. Performance improvement brought by neural networks

    Download full size
    Tools

    Get Citation

    Copy Citation Text

    Kai Song, Hongrui Liu, Yaoxing Bian, Shijun Zhao, Dong Wang, Liantuan Xiao. Deep Learning-Driven Single-Pixel Imaging: Advances and Challenges (Invited)[J]. Laser & Optoelectronics Progress, 2025, 62(17): 1739010

    Download Citation

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

    Category: AI for Optics

    Received: Mar. 17, 2025

    Accepted: Apr. 24, 2025

    Published Online: Sep. 16, 2025

    The Author Email: Yaoxing Bian (bianyaoxing@tyut.edu.cn), Liantuan Xiao (xlt@sxu.edu.cn)

    DOI:10.3788/LOP250831

    CSTR:32186.14.LOP250831

    Topics

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