Deep learning-based optical vector-eigenmode processing

被引:0
|
作者
Wen, Feng [1 ]
Li, Jian-Jun [1 ]
Diaol, Shui-Qiu [1 ]
Yang, Feng [2 ]
机构
[1] Univ Elect Sci & Technol China, Key Lab Opt Fiber Sensing & Commun Networks, Minist Educ, Chengdu 611731, Peoples R China
[2] Marolabs Co Ltd, Lab Holog Opt Sensing, Chengdu 610041, Peoples R China
关键词
deep-learning; optical vector-eigenmode decomposition; ResNet; generative adversarial network; MODE DECOMPOSITION; FIBERS;
D O I
10.1109/ICTON62926.2024.10647876
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Optical vector-eigenmode processing for no matter few-mode fibre- or free-space-based systems is crucial to the optical information processing (OIP). In this paper, we review our latest research on the application of deep-learning in laser communications. Firstly, we introduce the deep-learning approach into the vector-eigenmode decomposition of few-mode-based transmission systems, and investigate the decomposition performance through ResNet in detail. Subsequently, we explore the laser communication in free space, where the atmospheric turbulence causes the distortion of the received beam. We employ the generative adversarial network (GAN) to achieve the image restoration, resulting into an accurate reconstruction outcome.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Optical vector-eigenmode decomposition for few-mode fibers through deep learning networks
    Li, Jian-Jun
    Zhang, Rui
    Wen, Feng
    Yang, Feng
    Wu, Bao-Jian
    Qiu, Kun
    OPTICS COMMUNICATIONS, 2024, 564
  • [2] Deep learning-based image processing in optical microscopy
    Melanthota, Sindhoora Kaniyala
    Gopal, Dharshini
    Chakrabarti, Shweta
    Kashyap, Anirudh Ameya
    Radhakrishnan, Raghu
    Mazumder, Nirmal
    BIOPHYSICAL REVIEWS, 2022, 14 (02) : 463 - 481
  • [3] Deep learning-based image processing in optical microscopy
    Sindhoora Kaniyala Melanthota
    Dharshini Gopal
    Shweta Chakrabarti
    Anirudh Ameya Kashyap
    Raghu Radhakrishnan
    Nirmal Mazumder
    Biophysical Reviews, 2022, 14 : 463 - 481
  • [4] Experimental validation for high-order vector-eigenmode decomposition with polarization characteristics
    赵慧慧
    王思俨
    黄彦承
    陈伟
    庞拂飞
    曾祥龙
    Chinese Optics Letters, 2024, 22 (11) : 18 - 22
  • [5] Experimental validation for high-order vector-eigenmode decomposition with polarization characteristics
    Zhao, Huihui
    Wang, Siyan
    Huang, Yancheng
    Chen, Wei
    Pang, Fufei
    Zeng, Xianglong
    CHINESE OPTICS LETTERS, 2024, 22 (11)
  • [6] A Survey of Deep Learning-Based Mesh Processing
    He Wang
    Juyong Zhang
    Communications in Mathematics and Statistics, 2022, 10 : 163 - 194
  • [7] A Survey of Deep Learning-Based Mesh Processing
    Wang, He
    Zhang, Juyong
    COMMUNICATIONS IN MATHEMATICS AND STATISTICS, 2022, 10 (01) : 163 - 194
  • [8] CNN deep learning-based image to vector depiction
    Waheed, Safa Riyadh
    Rahim, Mohd Shafry Mohd
    Suaib, Norhaida Mohd
    Salim, A. A.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (13) : 20283 - 20302
  • [9] Deep Learning-based Image Text Processing Research
    Xiong, Huixuan
    Jin, Kai
    Liu, Jingnian
    Cai, Jiahong
    Xiao, Lijun
    2023 IEEE 9TH INTL CONFERENCE ON BIG DATA SECURITY ON CLOUD, BIGDATASECURITY, IEEE INTL CONFERENCE ON HIGH PERFORMANCE AND SMART COMPUTING, HPSC AND IEEE INTL CONFERENCE ON INTELLIGENT DATA AND SECURITY, IDS, 2023, : 163 - 168
  • [10] Analogical Reasoning With Deep Learning-Based Symbolic Processing
    Honda, Hiroshi
    Hagiwara, Masafumi
    IEEE ACCESS, 2021, 9 : 121859 - 121870