Laser & Optoelectronics Progress, Volume. 62, Issue 15, 1500009(2025)

Research Advances on Unsupervised Networks-Driven Imaging Through Scattering Media (Invited)

Longyu Qiao1, Bing Lin1, Xueqiang Fan1, Xixun Sun1,2, Zhiyong Peng2, and Zhongyi Guo1、*
Author Affiliations
  • 1School of Computer and Information, Hefei University of Technology, Hefei 230601, Anhui , China
  • 2Tianjin Jinhang Institute of Technical Physics, Tianjin 300192, China
  • show less

    Deep learning-based imaging through scattering media has emerged as a crucial research direction in computational optical imaging, garnering significant attention in recent years. While supervised learning approaches have made notable progress in this field, they still face numerous challenges in practical applications and key technologies. For instance, supervised learning heavily relies on precisely paired training data, which is extremely difficult and impractical to obtain in complex scattering environments. Moreover, supervised imaging methods often demonstrate poor generalization performance when confronting scenarios outside their training scope, due to the limited representational capacity of data samples. To address these challenges, unsupervised training strategies for imaging through scattering media have gradually become a research focus, yielding remarkable results. This paper classifies various network frameworks in unsupervised learning-based scattering media imaging from a neural network perspective. We categorize existing unsupervised learning-driven scattering imaging techniques into four types: autoencoder-based, generative adversarial network-based, diffusion model-based, and convolutional neural network-based unsupervised scattering imaging technologies. For each method, we provide detailed analysis of their performance advantages and limitations. Finally, we present future development prospects for neural network-based unsupervised imaging through scattering media. This review aims to help researchers understand the principles and latest developments in various unsupervised scattering media imaging techniques, clarify the characteristics and applicable scenarios of different technologies, thereby advancing the engineering application process of scattering media imaging technology.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Longyu Qiao, Bing Lin, Xueqiang Fan, Xixun Sun, Zhiyong Peng, Zhongyi Guo. Research Advances on Unsupervised Networks-Driven Imaging Through Scattering Media (Invited)[J]. Laser & Optoelectronics Progress, 2025, 62(15): 1500009

    Download Citation

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

    Category: Reviews

    Received: Apr. 9, 2025

    Accepted: May. 13, 2025

    Published Online: Aug. 6, 2025

    The Author Email: Zhongyi Guo (guozhongyi@hfut.edu.cn)

    DOI:10.3788/LOP250975

    CSTR:32186.14.LOP250975

    Topics