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 is a classical computer vision problem aiming torecover normal-exposure images from low-light images. However, convolutionalneural networks commonly used in this field are good at sampling low-frequencylocal structural features in the spatial domain, which leads to unclear texturedetails of the reconstructed images. To alleviate this problem, we propose anovel module using the Fourier coefficients, which can recover high-qualitytexture details under the constraint of semantics in the frequency phase andsupplement the spatial domain. In addition, we design a simple and efficientmodule for the image spatial domain using dilated convolutions with differentreceptive fields to alleviate the loss of detail caused by frequentdownsampling. We integrate the above parts into an end-to-end dual branchnetwork and design a novel loss committee and an adaptive fusion module toguide the network to flexibly combine spatial and frequency domain features togenerate more pleasing visual effects. Finally, we evaluate the proposednetwork on public benchmarks. Extensive experimental results show that ourmethod outperforms many existing state-of-the-art ones, showing outstandingperformance and potential.

DPFNet: A Dual-branch Dilated Network with Phase-aware Fourier Convolution for Low-light Image Enhancement