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

When capturing and storing images, devices inevitably introduce noise.Reducing this noise is a critical task called image denoising. Deep learninghas become the de facto method for image denoising, especially with theemergence of Transformer-based models that have achieved notablestate-of-the-art results on various image tasks. However, deep learning-basedmethods often suffer from a lack of generalization ability. For example, deepmodels trained on Gaussian noise may perform poorly when tested on other noisedistributions. To address this issue, we present a novel approach to enhancethe generalization performance of denoising networks, known as masked training.Our method involves masking random pixels of the input image and reconstructingthe missing information during training. We also mask out the features in theself-attention layers to avoid the impact of training-testing inconsistency.Our approach exhibits better generalization ability than other deep learningmodels and is directly applicable to real-world scenarios. Additionally, ourinterpretability analysis demonstrates the superiority of our method.

Masked Image Training for Generalizable Deep Image Denoising