Machine learning for avoiding stagnation in image-based wavefront sensing

Paine, Scott W.; Fienup, James R.

doi:10.1117/12.2519884

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The calibration of instrumental aberrations, through phase diversity approaches, [30][31][32] focal plane sharpening 33 techniques, or even Deep-learning strategies, 34,35 is particularly challenging. First of all, sampling the instrumental aberrations across the fov is feasible by the use of internal fibers within the system, 36,37 but can be potentially time consuming and requires direct control of the system.…”

Section: Scope On Advanced Psf Models and Reconstruction Techniquesmentioning

confidence: 99%

Review of PSF reconstruction methods and application to post-processing

Beltramo-Martin

Ragland

Fétick

et al. 2020

Adaptive Optics Systems VII

View full text Add to dashboard Cite

Determining the PSF remains a key challenge for post adaptive-optics (AO) observations regarding the spatial, temporal and spectral variabilities of the AO PSF, as well as itx complex structure. This paper aims to provide a non-exhaustive but classified list of techniques and references that address this issue of PSF determination, with a particular scope on PSF reconstruction, or more generally pupil-plane-based approaches. We have compiled a large amount of references to synthesize the main messages and kept them at a top level. We also present applications of PSF reconstruction/models to post-processing, more especially PSF-fitting and deconvolution for which there is a fast progress in the community.

show abstract

Section: Scope On Advanced Psf Models and Reconstruction Techniquesmentioning

confidence: 99%

Review of PSF reconstruction methods and application to post-processing

Beltramo-Martin

Ragland

Fétick

et al. 2020

Adaptive Optics Systems VII

View full text Add to dashboard Cite

show abstract

Phase-diversity wavefront sensing enhanced by a Fourier-based neural network

Zhou

Zhang

Fu³

et al. 2022

Opt. Express

View full text Add to dashboard Cite

Phase diversity wavefront sensing (PDWS) has been a successful approach to quantifying wavefront aberrations with only a few intensity measurements and nonlinear optimization. However, the inherent non-convexity of the inverse problem may lead to stagnation at a local minimum far from the true solution. Proper initialization of the nonlinear optimization is important to avoid local minima and improve wavefront retrieval accuracy. In this paper, we propose an effective neural network based on low-frequency coefficients in the Fourier domain to determine a better estimate of the unknown aberrations. By virtue of the proposed network, only a small amount of simulation data suffice for a robust training, two orders of magnitude less than those in existing work. Experimental results show that, when compared with some existing methods, our method achieves the highest accuracy while drastically reducing the training time to 1.4 min. The minimum, maximum, and mean values of the root mean square (RMS) residual errors for 800 aberrations are 0.017λ, 0.056λ, and 0.039λ, respectively, and 95% of the RMS residual errors are less than 0.05λ.

show abstract

Generalization of learned Fourier-based phase-diversity wavefront sensing

Zhou

Fu²,

Zhang

et al. 2023

Opt. Express

View full text Add to dashboard Cite

Proper initialization of the nonlinear optimization is important to avoid local minima in phase diversity wavefront sensing (PDWS). An effective neural network based on low-frequency coefficients in the Fourier domain has proved effective to determine a better estimate of the unknown aberrations. However, the network relies significantly on the training settings, such as imaging object and optical system parameters, resulting in a weak generalization ability. Here we propose a generalized Fourier-based PDWS method by combining an object-independent network with a system-independent image processing procedure. We demonstrate that a network trained with a specific setting can be applied to any image regardless of the actual settings. Experimental results show that a network trained with one setting can be applied to images with four other settings. For 1000 aberrations with RMS wavefront errors bounded within [0.2 λ, 0.4 λ], the mean RMS residual errors are 0.032 λ, 0.039 λ, 0.035 λ, and 0.037 λ, respectively, and 98.9% of the RMS residual errors are less than 0.05 λ.

show abstract

Machine learning for avoiding stagnation in image-based wavefront sensing

Cited by 4 publications

References 18 publications

Review of PSF reconstruction methods and application to post-processing

Review of PSF reconstruction methods and application to post-processing

Phase-diversity wavefront sensing enhanced by a Fourier-based neural network

Generalization of learned Fourier-based phase-diversity wavefront sensing

Contact Info

Product

Resources

About