Accelerating ptychographic reconstructions using spectral initializations
Lorenzo Valzania, Jonathan Dong, Sylvain Gigan
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 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.
Topics & Concepts
Phase retrievalPtychographyOpticsGradient descentPhysicsPhase (matter)AlgorithmIterative methodStochastic gradient descentComputer scienceInverse problemImage processingIterative reconstructionComputationFourier transformSpectral imagingSignal processingMethod of steepest descentArtificial neural networkSpectral methodData processingPhase modulationAdvanced X-ray Imaging TechniquesDigital Holography and MicroscopyAdvanced Electron Microscopy Techniques and Applications