Accelerating ptychographic reconstructions using spectral initializations

TL;DR

This paper demonstrates that spectral initializations significantly accelerate ptychographic reconstructions and improve noise resilience, achieving three times faster results without extra computational costs.

Contribution

It introduces the first application of spectral initializations to experimental ptychography, enhancing speed and robustness of phase retrieval algorithms.

Findings

Achieved threefold faster reconstructions with spectral methods

Improved noise resilience in ptychographic imaging

Spectral methods require no additional computational cost

Abstract

Ptychography is a promising phase retrieval technique for label-free quantitative phase imaging. Recent advances in phase retrieval algorithms witnessed the development of spectral methods, in order to accelerate gradient descent algorithms. Using spectral initializations on experimental data, for the first time we report three times faster ptychographic reconstructions than with a standard gradient descent algorithm and improved resilience to noise. Coming at no additional computational cost compared to gradient-descent-based algorithms, spectral methods have the potential to be implemented in large-scale iterative ptychographic algorithms.