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

Layer decomposition to separate an input image into base and detail layershas been steadily used for image restoration. Existing residual networks basedon an additive model require residual layers with a small output range for fastconvergence and visual quality improvement. However, in inverse halftoning,homogenous dot patterns hinder a small output range from the residual layers.Therefore, a new layer decomposition network based on the Gaussian convolutionmodel (GCM) and structure-aware deblurring strategy is presented to achieveresidual learning for both the base and detail layers. For the base layer, anew GCM-based residual subnetwork is presented. The GCM utilizes a statisticaldistribution, in which the image difference between a blurred continuous-toneimage and a blurred halftoned image with a Gaussian filter can result in anarrow output range. Subsequently, the GCM-based residual subnetwork uses aGaussian-filtered halftoned image as input and outputs the image difference asresidual, thereby generating the base layer, i.e., the Gaussian-blurredcontinuous-tone image. For the detail layer, a new structure-aware residualdeblurring subnetwork (SARDS) is presented. To remove the Gaussian blurring ofthe base layer, the SARDS uses the predicted base layer as input and outputsthe deblurred version. To more effectively restore image structures such aslines and texts, a new image structure map predictor is incorporated into thedeblurring network to induce structure-adaptive learning. This paper provides amethod to realize the residual learning of both the base and detail layersbased on the GCM and SARDS. In addition, it is verified that the proposedmethod surpasses state-of-the-art methods based on U-Net, direct deblurringnetworks, and progressively residual networks.

Layer Decomposition Learning Based on Gaussian Convolution Model and Residual Deblurring for Inverse Halftoning