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

Abstract

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.

arXiv comment8 pages, 4 figures

References in corpus (6)

• X-ray image reconstruction from a diffraction pattern alone
• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• Low Photon Count Phase Retrieval Using Deep Learning
• Measurement-based estimation of global pupil functions in 3D localization microscopy
• Phase Retrieval: An Overview of Recent Developments
• High precision wavefront control in point spread function engineering for single emitter localization

Cited by in corpus (4)

• Practical sensorless aberration estimation for 3D microscopy with deep learning
• Addressing systematic errors in axial distance measurements in single-emitter localization microscopy
• Learning to do multiframe wavefront sensing unsupervisedly: applications to blind deconvolution
• Learning an optimal PSF-pair for ultra-dense 3D localization microscopy