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

Single image super-resolution (SISR) deals with a fundamental problem ofupsampling a low-resolution (LR) image to its high-resolution (HR) version.Last few years have witnessed impressive progress propelled by deep learningmethods. However, one critical challenge faced by existing methods is to strikea sweet spot of deep model complexity and resulting SISR quality. This paperaddresses this pain point by proposing a linearly-assembled pixel-adaptiveregression network (LAPAR), which casts the direct LR to HR mapping learninginto a linear coefficient regression task over a dictionary of multiplepredefined filter bases. Such a parametric representation renders our modelhighly lightweight and easy to optimize while achieving state-of-the-artresults on SISR benchmarks. Moreover, based on the same idea, LAPAR is extendedto tackle other restoration tasks, e.g., image denoising and JPEG imagedeblocking, and again, yields strong performance. The code is available athttps://github.com/dvlab-research/Simple-SR.

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond