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

Recent years have witnessed the tremendous development of fusing fiber-opticimaging with supervised deep learning to enable high-quality imaging ofhard-to-reach areas. Nevertheless, the supervised deep learning method imposesstrict constraints on fiber-optic imaging systems, where the input objects andthe fiber outputs have to be collected in pairs. To unleash the full potentialof fiber-optic imaging, unsupervised image reconstruction is in demand.Unfortunately, neither optical fiber bundles nor multimode fibers can achieve apoint-to-point transmission of the object with a high sampling density, as is aprerequisite for unsupervised image reconstruction. The recently proposeddisordered fibers offer a new solution based on the transverse Andersonlocalization. Here, we demonstrate unsupervised full-color imaging with acellular resolution through a meter-long disordered fiber in both transmissionand reflection modes. The unsupervised image reconstruction consists of twostages. In the first stage, we perform a pixel-wise standardization on thefiber outputs using the statistics of the objects. In the second stage, werecover the fine details of the reconstructions through a generativeadversarial network. Unsupervised image reconstruction does not need pairedimages, enabling a much more flexible calibration under various conditions. Ournew solution achieves full-color high-fidelity cell imaging within a workingdistance of at least 4 mm by only collecting the fiber outputs after an initialcalibration. High imaging robustness is also demonstrated when the disorderedfiber is bent with a central angle of 60{\deg}. Moreover, the cross-domaingenerality on unseen objects is shown to be enhanced with a diversified objectset.

Unsupervised Full-color Cellular Image Reconstruction through Disordered Optical Fiber