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

Inspired by certain optimization solvers, the deep unfolding network (DUN)has attracted much attention in recent years for image compressed sensing (CS).However, there still exist the following two issues: 1) In existing DUNs, mosthyperparameters are usually content independent, which greatly limits theiradaptability for different input contents. 2) In each iteration, a plainconvolutional neural network is usually adopted, which weakens the perceptionof wider context prior and therefore depresses the expressive ability. In thispaper, inspired by the traditional Proximal Gradient Descent (PGD) algorithm, anovel DUN for image compressed sensing (dubbed DUN-CSNet) is proposed to solvethe above two issues. Specifically, for the first issue, a novel contentadaptive gradient descent network is proposed, in which a well-designed stepsize generation sub-network is developed to dynamically allocate thecorresponding step sizes for different textures of input image by generating acontent-aware step size map, realizing a content-adaptive gradient updating.For the second issue, considering the fact that many similar patches exist inan image but have undergone a deformation, a novel deformation-invariantnon-local proximal mapping network is developed, which can adaptively build thelong-range dependencies between the nonlocal patches by deformation-invariantnon-local modeling, leading to a wider perception on context priors. Extensiveexperiments manifest that the proposed DUN-CSNet outperforms existingstate-of-the-art CS methods by large margins.

Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling