Uncertainty quantification for ptychography using normalizing flows

TL;DR

This paper introduces a novel deep learning approach using normalizing flows to quantify uncertainty in ptychography reconstructions, improving the assessment of reconstruction quality without ground truth.

Contribution

It presents the first application of normalizing flows for uncertainty quantification in ptychography, addressing a key challenge in high-dimensional inverse problems.

Findings

Effective uncertainty characterization demonstrated on synthetic data.

Robust performance across various experimental settings.

Enhanced ability to detect artifacts and guide experiments.

Abstract

Ptychography, as an essential tool for high-resolution and nondestructive material characterization, presents a challenging large-scale nonlinear and non-convex inverse problem; however, its intrinsic photon statistics create clear opportunities for statistical-based deep learning approaches to tackle these challenges, which has been underexplored. In this work, we explore normalizing flows to obtain a surrogate for the high-dimensional posterior, which also enables the characterization of the uncertainty associated with the reconstruction: an extremely desirable capability when judging the reconstruction quality in the absence of ground truth, spotting spurious artifacts and guiding future experiments using the returned uncertainty patterns. We demonstrate the performance of the proposed method on a synthetic sample with added noise and in various physical experimental settings.