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

While deep neural networks exhibit state-of-the-art results in the task ofimage super-resolution (SR) with a fixed known acquisition process (e.g., abicubic downscaling kernel), they experience a huge performance loss when thereal observation model mismatches the one used in training. Recently, twodifferent techniques suggested to mitigate this deficiency, i.e., enjoy theadvantages of deep learning without being restricted by the training phase. Thefirst one follows the plug-and-play (P&P) approach that solves general inverseproblems (e.g., SR) by using Gaussian denoisers for handling the prior term inmodel-based optimization schemes. The second builds on internal recurrence ofinformation inside a single image, and trains a super-resolver network at testtime on examples synthesized from the low-resolution image. Our workincorporates these two independent strategies, enjoying the impressivegeneralization capabilities of deep learning, captured by the first, andfurther improving it through internal learning at test time. First, we apply arecent P&P strategy to SR. Then, we show how it may become image-adaptive intest time. This technique outperforms the above two strategies on populardatasets and gives better results than other state-of-the-art methods inpractical cases where the observation model is inexact or unknown in advance.

Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning