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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Digital holography is a 3D imaging technique by emitting a laser beam with aplane wavefront to an object and measuring the intensity of the diffractedwaveform, called holograms. The object's 3D shape can be obtained by numericalanalysis of the captured holograms and recovering the incurred phase. Recently,deep learning (DL) methods have been used for more accurate holographicprocessing. However, most supervised methods require large datasets to trainthe model, which is rarely available in most DH applications due to thescarcity of samples or privacy concerns. A few one-shot DL-based recoverymethods exist with no reliance on large datasets of paired images. Still, mostof these methods often neglect the underlying physics law that governs wavepropagation. These methods offer a black-box operation, which is notexplainable, generalizable, and transferrable to other samples andapplications. In this work, we propose a new DL architecture based ongenerative adversarial networks that uses a discriminative network forrealizing a semantic measure for reconstruction quality while using agenerative network as a function approximator to model the inverse of hologramformation. We impose smoothness on the background part of the recovered imageusing a progressive masking module powered by simulated annealing to enhancethe reconstruction quality. The proposed method is one of its kind thatexhibits high transferability to similar samples, which facilitates its fastdeployment in time-sensitive applications without the need for retraining thenetwork. The results show a considerable improvement to competitor methods inreconstruction quality (about 5 dB PSNR gain) and robustness to noise (about50% reduction in PSNR vs noise increase rate).

DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography