TY - JOUR
T1 - Boosting the deep learning wavefront sensor for real-time applications [Invited]
AU - VERA ROJAS, ESTEBAN MAURICIO
AU - Guzmán, Felipe
AU - Weinberger, Camilo
N1 - Publisher Copyright:
© 2021 Optical Society of America.
PY - 2021/4/1
Y1 - 2021/4/1
N2 - The deep learning wavefront sensor (DLWFS) allows the direct estimate of Zernike coefficients of aberrated wavefronts from intensity images. The main drawback of this approach is related to the use of massive convolutional neural networks (CNNs) that are lengthy to train or estimate. In this paper, we explore several options to reduce both the training and estimation time. First, we develop a CNN that can be rapidly trained without compromising accuracy. Second, we explore the effects given smaller input image sizes and different amounts of Zernike modes to be estimated. Our simulation results demonstrate that the proposed network using images of either 8×8, 16×16, or 32×32 will dramatically reduce training time and even boost the estimation accuracy of Zernike coefficients. From our experimental results, we can confirm that a 16×16 DLWFS can be quickly trained and is able to estimate the first 12 Zernike coefficients-skipping piston, tip, and tilt-without sacrificing accuracy and significantly speeding up the prediction time to facilitate low-cost, real-time adaptive optics systems.
AB - The deep learning wavefront sensor (DLWFS) allows the direct estimate of Zernike coefficients of aberrated wavefronts from intensity images. The main drawback of this approach is related to the use of massive convolutional neural networks (CNNs) that are lengthy to train or estimate. In this paper, we explore several options to reduce both the training and estimation time. First, we develop a CNN that can be rapidly trained without compromising accuracy. Second, we explore the effects given smaller input image sizes and different amounts of Zernike modes to be estimated. Our simulation results demonstrate that the proposed network using images of either 8×8, 16×16, or 32×32 will dramatically reduce training time and even boost the estimation accuracy of Zernike coefficients. From our experimental results, we can confirm that a 16×16 DLWFS can be quickly trained and is able to estimate the first 12 Zernike coefficients-skipping piston, tip, and tilt-without sacrificing accuracy and significantly speeding up the prediction time to facilitate low-cost, real-time adaptive optics systems.
UR - http://www.scopus.com/inward/record.url?scp=85103469648&partnerID=8YFLogxK
U2 - 10.1364/AO.417574
DO - 10.1364/AO.417574
M3 - Article
AN - SCOPUS:85103469648
VL - 60
SP - B119-B124
JO - Applied Optics
JF - Applied Optics
SN - 1559-128X
IS - 10
ER -