Year
Month
(Peer-Reviewed) Physics-informed deep learning for fringe pattern analysis
Wei Yin 尹维 ¹ ² ³, Yuxuan Che 车宇轩 ¹ ² ³, Xinsheng Li 李鑫胜 ¹ ² ³, Mingyu Li 李明雨 ¹ ² ³, Yan Hu 胡岩 ¹ ² ³, Shijie Feng 冯世杰 ¹ ² ³, Edmund Y. Lam 林彥民 ⁴, Qian Chen 陈钱 ³, Chao Zuo 左超 ¹ ² ³
¹ Smart Computational Imaging Laboratory (SCILab), School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
中国 南京 南京理工大学光电信息科学与工程学院 智能计算成像实验室
² Smart Computational Imaging Research Institute (SCIRI) of Nanjing University of Science and Technology, Nanjing 210019, China
中国 南京 南京理工大学智能计算成像研究院
³ Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense, Nanjing 210094, China
中国 南京 江苏省光谱成像与智能感知重点实验室
⁴ Department of Electrical and Electronic Engineering, The University of Hong Kong, Pokfulam, Hong Kong SAR 999077, China
中国 香港 薄扶林 香港大学电气电子工程系
Opto-Electronic Advances, 2024-01-25
Abstract

Recently, deep learning has yielded transformative success across optics and photonics, especially in optical metrology. Deep neural networks (DNNs) with a fully convolutional architecture (e.g., U-Net and its derivatives) have been widely implemented in an end-to-end manner to accomplish various optical metrology tasks, such as fringe denoising, phase unwrapping, and fringe analysis.

However, the task of training a DNN to accurately identify an image-to-image transform from massive input and output data pairs seems at best naïve, as the physical laws governing the image formation or other domain expertise pertaining to the measurement have not yet been fully exploited in current deep learning practice.

To this end, we introduce a physics-informed deep learning method for fringe pattern analysis (PI-FPA) to overcome this limit by integrating a lightweight DNN with a learning-enhanced Fourier transform profilometry (LeFTP) module. By parameterizing conventional phase retrieval methods, the LeFTP module embeds the prior knowledge in the network structure and the loss function to directly provide reliable phase results for new types of samples, while circumventing the requirement of collecting a large amount of high-quality data in supervised learning methods. Guided by the initial phase from LeFTP, the phase recovery ability of the lightweight DNN is enhanced to further improve the phase accuracy at a low computational cost compared with existing end-to-end networks. Experimental results demonstrate that PI-FPA enables more accurate and computationally efficient single-shot phase retrieval, exhibiting its excellent generalization to various unseen objects during training.

The proposed PI-FPA presents that challenging issues in optical metrology can be potentially overcome through the synergy of physics-priors-based traditional tools and data-driven learning approaches, opening new avenues to achieve fast and accurate single-shot 3D imaging.
Physics-informed deep learning for fringe pattern analysis_1
Physics-informed deep learning for fringe pattern analysis_2
Physics-informed deep learning for fringe pattern analysis_3
Physics-informed deep learning for fringe pattern analysis_4
  • Ultrahigh performance passive radiative cooling by hybrid polar dielectric metasurface thermal emitters
  • Yinan Zhang, Yinggang Chen, Tong Wang, Qian Zhu, Min Gu
  • Opto-Electronic Advances
  • 2024-03-12
  • Simultaneously realizing thermal and electromagnetic cloaking by multi-physical null medium
  • Yichao Liu, Xiaomin Ma, Kun Chao, Fei Sun, Zihao Chen, Jinyuan Shan, Hanchuan Chen, Gang Zhao, Shaojie Chen
  • Opto-Electronic Science
  • 2024-02-29
  • Generation of lossy mode resonances (LMR) using perovskite nanofilms
  • Dayron Armas, Ignacio R. Matias, M. Carmen Lopez-Gonzalez, Carlos Ruiz Zamarreño, Pablo Zubiate, Ignacio del Villar, Beatriz Romero
  • Opto-Electronic Advances
  • 2024-02-26
  • Acousto-optic scanning multi-photon lithography with high printing rate
  • Minghui Hong
  • Opto-Electronic Advances
  • 2024-02-26
  • Tailoring electron vortex beams with customizable intensity patterns by electron diffraction holography
  • Pengcheng Huo, Ruixuan Yu, Mingze Liu, Hui Zhang, Yan-qing Lu, Ting Xu
  • Opto-Electronic Advances
  • 2024-02-26
  • Miniature tunable Airy beam optical meta-device
  • Jing Cheng Zhang, Mu Ku Chen, Yubin Fan, Qinmiao Chen, Shufan Chen, Jin Yao, Xiaoyuan Liu, Shumin Xiao, Din Ping Tsai
  • Opto-Electronic Advances
  • 2024-02-26
  • Data-driven polarimetric imaging: a review
  • Kui Yang, Fei Liu, Shiyang Liang, Meng Xiang, Pingli Han, Jinpeng Liu, Xue Dong, Yi Wei, Bingjian Wang, Koichi Shimizu, Xiaopeng Shao
  • Opto-Electronic Science
  • 2024-02-24
  • Towards the performance limit of catenary meta-optics via field-driven optimization
  • Siran Chen, Yingli Ha, Fei Zhang, Mingbo Pu, Hanlin Bao, Mingfeng Xu, Yinghui Guo, Yue Shen, Xiaoliang Ma, Xiong Li, Xiangang Luo
  • Opto-Electronic Advances
  • 2024-01-31
  • Broadband high-efficiency dielectric metalenses based on quasi-continuous nanostrips
  • Xiaohu Zhang, Qinmiao Chen, Dongliang Tang, Kaifeng Liu, Haimo Zhang, Lintong Shi, Mengyao He, Yongcai Guo, Shumin Xiao
  • Opto-Electronic Advances
  • 2024-01-31
  • Robust measurement of orbital angular momentum of a partially coherent vortex beam under amplitude and phase perturbations
  • Zhao Zhang, Gaoyuan Li, Yonglei Liu, Haiyun Wang, Bernhard J. Hoenders, Chunhao Liang, Yangjian Cai, Jun Zeng
  • Opto-Electronic Science
  • 2024-01-31
  • Deblurring, artifact-free optical coherence tomography with deconvolution-random phase modulation
  • Xin Ge, Si Chen, Kan Lin, Guangming Ni, En Bo, Lulu Wang, Linbo Liu
  • Opto-Electronic Science
  • 2024-01-31
  • Dynamic interactive bitwise meta-holography with ultra-high computational and display frame rates
  • Yuncheng Liu, Ke Xu, Xuhao Fan, Xinger Wang, Xuan Yu, Wei Xiong, Hui Gao
  • Opto-Electronic Advances
  • 2024-01-25



  • Multi-dimensional multiplexing optical secret sharing framework with cascaded liquid crystal holograms                                Smart palm-size optofluidic hematology analyzer for automated imaging-based leukocyte concentration detection
    About
    |
    Contact
    |
    Copyright © PubCard