Super-resolution reconstruction for far-field beam profile based on deep learning

Xianchen Xie; Bolang Fang; Haichuan Zhao; Dahui Wang; Pengling Yang

doi:10.1117/12.2657038

22 December 2022 Super-resolution reconstruction for far-field beam profile based on deep learning

Xianchen Xie, Bolang Fang, Haichuan Zhao, Dahui Wang, Pengling Yang

Proceedings Volume 12459, Sixth International Symposium on Laser Interaction with Matter; 124591F (2022) https://doi.org/10.1117/12.2657038
Event: Sixth International Symposium on Laser Interaction with Matter (LIMIS 2022), 2022, Ningbo, China

Abstract

In order to obtain more information of far-field beam profile from limited measured data, a novel super-resolution reconstruction method for far-field beam profile based on deep learning is proposed. In this paper, the high/low resolution spot image sample is obtained by simulation, the EDSR neural network training model is used to study the mapping relationship between high/ low resolution spot images, and the super-resolution reconstruction method based on deep learning is realized. The experimental results show that the super-resolution reconstruction based on deep learning is superior to the conventional algorithms in PSNR and SSIM.

Citation Download Citation

Xianchen Xie, Bolang Fang, Haichuan Zhao, Dahui Wang, and Pengling Yang "Super-resolution reconstruction for far-field beam profile based on deep learning", Proc. SPIE 12459, Sixth International Symposium on Laser Interaction with Matter, 124591F (22 December 2022); https://doi.org/10.1117/12.2657038

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available