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.
Agnimitra Dasgupta (University of Southern California)
I am a PhD candidate and Provost Fellow at the Sonny Astani Department of Civil & Environmental Engineering, University of Southern California. My research interests lie at the intersection of uncertainty quantification, statistical learning and scientific machine learning with applications in problems ranging from imaging to mechanics.
More from the Same Authors
2022 : GAN-Flow: A dimension-reduced variational framework for physics-based inverse problems »
Agnimitra Dasgupta · Dhruv Patel · Deep Ray · Erik Johnson · Assad Oberai