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

The goal of this paper is to present a non-iterative and more importantly anextremely fast algorithm to reconstruct images from compressively sensed (CS)random measurements. To this end, we propose a novel convolutional neuralnetwork (CNN) architecture which takes in CS measurements of an image as inputand outputs an intermediate reconstruction. We call this network, ReconNet. Theintermediate reconstruction is fed into an off-the-shelf denoiser to obtain thefinal reconstructed image. On a standard dataset of images we show significantimprovements in reconstruction results (both in terms of PSNR and timecomplexity) over state-of-the-art iterative CS reconstruction algorithms atvarious measurement rates. Further, through qualitative experiments on realdata collected using our block single pixel camera (SPC), we show that ournetwork is highly robust to sensor noise and can recover visually betterquality images than competitive algorithms at extremely low sensing rates of0.1 and 0.04. To demonstrate that our algorithm can recover semanticallyinformative images even at a low measurement rate of 0.01, we present a veryrobust proof of concept real-time visual tracking application.

ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements