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

Light-field microscopes are able to capture spatial and angular informationof incident light rays. This allows reconstructing 3D locations of neurons froma single snap-shot.In this work, we propose a model-inspired deep learningapproach to perform fast and robust 3D localization of sources usinglight-field microscopy images. This is achieved by developing a deep networkthat efficiently solves a convolutional sparse coding (CSC) problem to mapEpipolar Plane Images (EPI) to corresponding sparse codes. The networkarchitecture is designed systematically by unrolling the convolutionalIterative Shrinkage and Thresholding Algorithm (ISTA) while the networkparameters are learned from a training dataset. Such principled design enablesthe deep network to leverage both domain knowledge implied in the model, aswell as new parameters learned from the data, thereby combining advantages ofmodel-based and learning-based methods. Practical experiments on localizationof mammalian neurons from light-fields show that the proposed approachsimultaneously provides enhanced performance, interpretability and efficiency.

Model-inspired Deep Learning for Light-Field Microscopy with Application to Neuron Localization