Design and training of a deep neural network for estimating the optical gain in pyramid wavefront sensors

Camilo Weinberger, Felipe Guzmán, Jorge Tapia, Benoit Neichel, Esteban Vera

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work shows the design and training of a convolutional neural network to improve the linear response of a modulated pyramid wavefront sensor, allowing to estimate and compensate for the optical gain in real time.

Original languageEnglish
Title of host publicationPropagation Through and Characterization of Atmospheric and Oceanic Phenomena, pcAOP 2022
PublisherOptica Publishing Group (formerly OSA)
ISBN (Electronic)9781557528209
StatePublished - 2022
Externally publishedYes
EventPropagation Through and Characterization of Atmospheric and Oceanic Phenomena, pcAOP 2022 - Vancouver, Canada
Duration: 11 Jul 202215 Jul 2022

Publication series

NameOptics InfoBase Conference Papers

Conference

ConferencePropagation Through and Characterization of Atmospheric and Oceanic Phenomena, pcAOP 2022
Country/TerritoryCanada
CityVancouver
Period11/07/2215/07/22

Fingerprint

Dive into the research topics of 'Design and training of a deep neural network for estimating the optical gain in pyramid wavefront sensors'. Together they form a unique fingerprint.

Cite this