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/

Zendy Plus

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

Zendy Tools

Zendy Open

Rain in the dark poses a significant challenge to deploying real-worldapplications such as autonomous driving, surveillance systems, and nightphotography. Existing low-light enhancement or deraining methods struggle tobrighten low-light conditions and remove rain simultaneously. Additionally,cascade approaches like ``deraining followed by low-light enhancement'' or thereverse often result in problematic rain patterns or overly blurred andoverexposed images. To address these challenges, we introduce an end-to-endmodel called L$^{2}$RIRNet, designed to manage both low-light enhancement andderaining in real-world settings. Our model features two main components: aDual Degradation Representation Network (DDR-Net) and a Restoration Network.The DDR-Net independently learns degradation representations for luminanceeffects in dark areas and rain patterns in light areas, employing dualdegradation loss to guide the training process. The Restoration Networkrestores the degraded image using a Fourier Detail Guidance (FDG) module, whichleverages near-rainless detailed images, focusing on texture details infrequency and spatial domains to inform the restoration process. Furthermore,we contribute a dataset containing both synthetic and real-worldlow-light-rainy images. Extensive experiments demonstrate that ourL$^{2}$RIRNet performs favorably against existing methods in both synthetic andcomplex real-world scenarios. All the code and dataset can be found in\url{https://github.com/linxin0/Low_light_rainy}.

Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark