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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The high-dimensional nature of the 4-D light field (LF) poses greatchallenges in achieving efficient and effective feature embedding, thatseverely impacts the performance of downstream tasks. To tackle this crucialissue, in contrast to existing methods with empirically-designed architectures,we propose a probabilistic-based feature embedding (PFE), which learns afeature embedding architecture by assembling various low-dimensionalconvolution patterns in a probability space for fully capturing spatial-angularinformation. Building upon the proposed PFE, we then leverage the intrinsiclinear imaging model of the coded aperture camera to construct acycle-consistent 4-D LF reconstruction network from coded measurements.Moreover, we incorporate PFE into an iterative optimization framework for 4-DLF denoising. Our extensive experiments demonstrate the significant superiorityof our methods on both real-world and synthetic 4-D LF images, bothquantitatively and qualitatively, when compared with state-of-the-art methods.The source code will be publicly available athttps://github.com/lyuxianqiang/LFCA-CR-NET.

Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising