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

Möckl L, Petrov PN, Moerner WE (2019)

Publication Type: Journal article

Publication year: 2019

Journal

Applied Physics Letters American Institute of Physics (AIP)

Book Volume: 115

Article Number: 251106

Journal Issue: 25

DOI: 10.1063/1.5125252

Abstract

Phase retrieval, i.e., the reconstruction of phase information from intensity information, is a central problem in many optical systems. Imaging the emission from a point source such as a single molecule is one example. Here, we demonstrate that a deep residual neural net is able to quickly and accurately extract the hidden phase for general point spread functions (PSFs) formed by Zernike-type phase modulations. Five slices of the 3D PSF at different focal positions within a two micrometer range around the focus are sufficient to retrieve the first six orders of Zernike coefficients.

Involved external institutions

Stanford University

United States (USA) (US)

How to cite

APA:

Möckl, L., Petrov, P.N., & Moerner, W.E. (2019). Accurate phase retrieval of complex 3D point spread functions with deep residual neural networks. Applied Physics Letters, 115(25). https://doi.org/10.1063/1.5125252

MLA:

Möckl, Leonhard, Petar N. Petrov, and W. E. Moerner. "Accurate phase retrieval of complex 3D point spread functions with deep residual neural networks." Applied Physics Letters 115.25 (2019).

BibTeX: Download