Improving the generalization ability of deep-learning-based wavefront sensing method to objects

Mengmeng Zhang; Jiwei Zhang; Zhenbo Ren; Shan Mao; Jianlin Zhao

doi:10.1117/12.2687293

29 November 2023 Improving the generalization ability of deep-learning-based wavefront sensing method to objects

Mengmeng Zhang, Jiwei Zhang, Zhenbo Ren, Shan Mao, Jianlin Zhao

Proceedings Volume 12768, Holography, Diffractive Optics, and Applications XIII; 1276824 (2023) https://doi.org/10.1117/12.2687293
Event: SPIE/COS Photonics Asia, 2023, Beijing, China

Conference Poster

Abstract

A deep neural network with differential architecture is proposed to reconstruct turbulence phases from single-shot intensity images of extended targets, and a phase spatial modulator (SLM) is used for wavefront correction. The neural network takes the inputs of an aberrated intensity image and a background image and separates the turbulence phase from the target structure by comparing the high-dimensional features of the two inputs. The SLM is used to simulate atmospheric turbulence in the optical path and for correction of the external turbulent field. This method is verified in the optical path with the flame field.

Citation Download Citation

Mengmeng Zhang, Jiwei Zhang, Zhenbo Ren, Shan Mao, and Jianlin Zhao "Improving the generalization ability of deep-learning-based wavefront sensing method to objects", Proc. SPIE 12768, Holography, Diffractive Optics, and Applications XIII, 1276824 (29 November 2023); https://doi.org/10.1117/12.2687293

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