• Photonics Research
  • Vol. 9, Issue 8, 0800B262 (2021)
Yunqi Luo1、†, Suxia Yan1、†, Huanhao Li2、3、†, Puxiang Lai2、3、4、*, and Yuanjin Zheng1、5、*
Author Affiliations
  • 1School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
  • 2Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
  • 3The Hong Kong Polytechnic University Shenzhen Research Institute, Shenzhen 518034, China
  • 4e-mail: puxiang.lai@polyu.edu.hk
  • 5e-mail: yjzheng@ntu.edu.sg
  • show less

    Abstract

    Optical focusing through scattering media is of great significance yet challenging in lots of scenarios, including biomedical imaging, optical communication, cybersecurity, three-dimensional displays, etc. Wavefront shaping is a promising approach to solve this problem, but most implementations thus far have only dealt with static media, which, however, deviates from realistic applications. Herein, we put forward a deep learning-empowered adaptive framework, which is specifically implemented by a proposed Timely-Focusing-Optical-Transformation-Net (TFOTNet), and it effectively tackles the grand challenge of real-time light focusing and refocusing through time-variant media without complicated computation. The introduction of recursive fine-tuning allows timely focusing recovery, and the adaptive adjustment of hyperparameters of TFOTNet on the basis of medium changing speed efficiently handles the spatiotemporal non-stationarity of the medium. Simulation and experimental results demonstrate that the adaptive recursive algorithm with the proposed network significantly improves light focusing and tracking performance over traditional methods, permitting rapid recovery of an optical focus from degradation. It is believed that the proposed deep learning-empowered framework delivers a promising platform towards smart optical focusing implementations requiring dynamic wavefront control.

    Copy Citation Text
    Yunqi Luo, Suxia Yan, Huanhao Li, Puxiang Lai, Yuanjin Zheng. Towards smart optical focusing: deep learning-empowered dynamic wavefront shaping through nonstationary scattering media[J]. Photonics Research, 2021, 9(8): 0800B262
    Download Citation
    Special Issue: DEEP LEARNING IN PHOTONICS
    Received: Nov. 20, 2020
    Accepted: Jan. 21, 2021
    Posted: Jan. 22, 2021
    Published Online: Jul. 22, 2021
    The Author Email: Puxiang Lai (puxiang.lai@polyu.edu.hk), Yuanjin Zheng (yjzheng@ntu.edu.sg)