English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Computational imaging is increasingly vital for a broad spectrum ofapplications, ranging from biological to material sciences. This includesapplications where the object is known and sufficiently sparse, allowing it tobe described with a reduced number of parameters. When no explicitparameterization is available, a deep generative model can be trained torepresent an object in a low-dimensional latent space. In this paper, weharness this dimensionality reduction capability of autoencoders to search forthe object solution within the latent space rather than the object space. Wedemonstrate a novel approach to ptychographic image reconstruction byintegrating a deep generative model obtained from a pre-trained autoencoderwithin an Automatic Differentiation Ptychography (ADP) framework. This approachenables the retrieval of objects from highly ill-posed diffraction patterns,offering an effective method for noise-robust latent vector reconstruction inptychography. Moreover, the mapping into a low-dimensional latent space allowsus to visualize the optimization landscape, which provides insight into theconvexity and convergence behavior of the inverse problem. With this work, weaim to facilitate new applications for sparse computational imaging such aswhen low radiation doses or rapid reconstructions are essential.

Noise-robust latent vector reconstruction in ptychography using deep generative models