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

Low-light image enhancement aims to improve the perception of imagescollected in dim environments and provide high-quality data support for imagerecognition tasks. When dealing with photos captured under non-uniformillumination, existing methods cannot adaptively extract the differentiatedluminance information, which will easily cause over-exposure andunder-exposure. From the perspective of unsupervised learning, we propose amulti-scale attention Transformer named MSATr, which sufficiently extractslocal and global features for light balance to improve the visual quality.Specifically, we present a multi-scale window division scheme, which usesexponential sequences to adjust the window size of each layer. Withindifferent-sized windows, the self-attention computation can be refined,ensuring the pixel-level feature processing capability of the model. Forfeature interaction across windows, a global transformer branch is constructedto provide comprehensive brightness perception and alleviate exposure problems.Furthermore, we propose a loop training strategy, using the diverse imagesgenerated by weighted mixing and a luminance consistency loss to improve themodel's generalization ability effectively. Extensive experiments on severalbenchmark datasets quantitatively and qualitatively prove that our MSATr issuperior to state-of-the-art low-light image enhancement methods, and theenhanced images have more natural brightness and outstanding details. The codeis released at https://github.com/fang001021/MSATr.

A Non-Uniform Low-Light Image Enhancement Method with Multi-Scale Attention Transformer and Luminance Consistency Loss