Machine learning for improved image-based wavefront sensing

Paine, Scott W.; Fienup, James R.

doi:10.1364/ol.43.001235

Cited by 160 publications

(71 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently machine learning based on convolutional neural network was proposed to get a good initial estimate of the wavefront and then achieve better convergence for a large amount of wavefront error. [ 163 ]…”

Section: Non‐interferometric Areal Measurementmentioning

confidence: 99%

Measurement of Freeform Optical Surfaces: Trade‐Off between Accuracy and Dynamic Range

Chen

Xue

Zhai

et al. 2020

Laser & Photonics Reviews

View full text Add to dashboard Cite

Freeform optical surfaces are advantageous to optical designers, as they provide additional degrees of freedom for optimization. The loss of rotational symmetry, however, makes measurement of freeforms more challenging. Herein, advances in interferometric areal measurement of freeform optical surfaces, including null tests, non-null tests, near-null tests, and adaptive null tests, are reviewed. Some new developments, in the Hartmann test, deflectometry, and phase retrieval, as representatives of non-interferometric areal measurement, are then presented. Overall, the focus is on single-point-probe-based profilometry categorized into coordinate measurements and slope-or curvature-based measurements. Innovative measurement technology is trying to bridge the gap between high accuracy and high dynamic range as freeform optical surfaces are finding more applications in visible and shorter-wavelength optics.

show abstract

Section: Non‐interferometric Areal Measurementmentioning

confidence: 99%

Measurement of Freeform Optical Surfaces: Trade‐Off between Accuracy and Dynamic Range

Chen

Xue

Zhai

et al. 2020

Laser & Photonics Reviews

View full text Add to dashboard Cite

show abstract

“…Architectures such as the Inception [23] and Xception [24] networks, on the other hand, excel at image classification tasks because they are able to recognize features at very different length scales. Though these architectures have been described for wavefront sensing [19,20], we suspected that these architectures could be improved for PR. Specifically, a single feature in a PSF image is by itself not necessarily indicative of the phase.…”

Section: Psf Simulationsmentioning

confidence: 99%

Accurate phase retrieval of complex 3D point spread functions with deep residual neural networks

Möckl

Petrov

Moerner

2019

Applied Physics Letters

View full text Add to dashboard Cite

Phase retrieval, i.e. the reconstruction of phase information from intensity information, is a central problem in many optical systems. Here, we demonstrate that a deep residual neural net is able to quickly and accurately perform this task for arbitrary point spread functions (PSFs) formed by Zernike-type phase modulations. Five slices of the 3D PSF at different focal positions within a two micron range around the focus are sufficient to retrieve the first six orders of Zernike coefficients.

show abstract

“…Some of these approaches use a blur kernel that includes focus and astigmatism only or use larger kernels that are not physically realisable in a microscope [11,12] and typically do not take advantage of additional information from phase-diverse images. Other approaches model the image estimation part with a CNN and use a deconvolution module [11,13] to extract the PSF, or use existing CNN architectures such as ResNet and Inception to regress Zernike coefficients [12,14,15], and use iterative Richardson-Lucy to estimate the image but not both.…”

Section: Introductionmentioning

confidence: 99%

“…On a related note, Paine et.al. trained an Inception model and its variant for estimating a good initial guess of the wavefront [14]. and Nishizaki et.al.…”

Section: Introductionmentioning

confidence: 99%

Optical Aberration Correction via Phase Diversity and Deep Learning

Krishnan

Belthangady

Nyby

et al. 2020

Preprint

View full text Add to dashboard Cite

In modern microscopy imaging systems, optical components are carefully designed to obtain diffraction-limited resolution. However, live imaging of large biological samples rarely attains this limit because of sample induced refractive index inhomogeneities that create unknown temporally variant optical aberrations. Importantly, these aberrations are also spatially variant, thus making it challenging to correct over wide fields of view. Here, we present a framework for deep-learning based wide-field optical aberration sensing and correction. Our model consists of two modules which take in a set of three phase-diverse images and (i) estimate the wavefront phase in terms of its constituent Zernike polynomial coefficients and (ii) perform blind-deconvolution to yield an aberration-free image. First, we demonstrate our framework on simulations that incorporate optical aberrations, spatial variance, and realistic modelling of sensor noise. We find that our blind deconvolution achieves a 2-fold improvement in frequency support compared to input images, and our phase-estimation achieves a coefficient of determination (r 2 ) of at least 80% when estimating astigmatism, spherical aberration and coma. Second, we show that our results mostly hold for strongly varying spatially-variant aberrations with a 30% resolution improvement. Third, we demonstrate practical usability for light-sheet microscopy: we show a 46% increase in frequency support even in imaging regions affected by detection and illumination scattering.

show abstract

Machine learning for improved image-based wavefront sensing

Cited by 160 publications

References 20 publications

Measurement of Freeform Optical Surfaces: Trade‐Off between Accuracy and Dynamic Range

Measurement of Freeform Optical Surfaces: Trade‐Off between Accuracy and Dynamic Range

Accurate phase retrieval of complex 3D point spread functions with deep residual neural networks

Optical Aberration Correction via Phase Diversity and Deep Learning

Contact Info

Product

Resources

About