Enhancing phase retrieval with domain adaptation: bridging the gap between simulations and real data

Maxime Quesnel; Gilles Orban de Xivry; Jyotirmay Paul; Olivier Absil; Gilles Louppe; Vincent Deo; Sébastien Vievard; Olivier Guyon

doi:10.1117/12.3019746

28 August 2024 Enhancing phase retrieval with domain adaptation: bridging the gap between simulations and real data

Maxime Quesnel, Gilles Orban de Xivry, Jyotirmay Paul, Olivier Absil, Gilles Louppe, Vincent Deo, Sébastien Vievard, Olivier Guyon

Author Affiliations +

Proceedings Volume 13097, Adaptive Optics Systems IX; 130970X (2024) https://doi.org/10.1117/12.3019746
Event: SPIE Astronomical Telescopes + Instrumentation, 2024, Yokohama, Japan

Abstract

High-contrast imaging instruments face performance limitations due to non-common path aberrations, which hinder the detection of exoplanets. We have successfully applied convolutional neural networks to estimate these aberrations using simulations. However, training a model on simulated data before inferring the phase aberrations on real data leads to inaccuracies. In this study, we propose a domain adaptation method, based on a variational autoencoder architecture, to swiftly adapt models from simulations to real data. We employ the Subaru/SCExAO instrument and showcase how our approach significantly enhances phase retrieval.

Conference Presentation

Citation Download Citation

Maxime Quesnel, Gilles Orban de Xivry, Jyotirmay Paul, Olivier Absil, Gilles Louppe, Vincent Deo, Sébastien Vievard, and Olivier Guyon "Enhancing phase retrieval with domain adaptation: bridging the gap between simulations and real data", Proc. SPIE 13097, Adaptive Optics Systems IX, 130970X (28 August 2024); https://doi.org/10.1117/12.3019746

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