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

Single image dehazing is a challenging ill-posed problem which estimateslatent haze-free images from observed hazy images. Some existing deep learningbased methods are devoted to improving the model performance via increasing thedepth or width of convolution. The learning ability of convolutional neuralnetwork (CNN) structure is still under-explored. In this paper, adetail-enhanced attention block (DEAB) consisting of the detail-enhancedconvolution (DEConv) and the content-guided attention (CGA) is proposed toboost the feature learning for improving the dehazing performance.Specifically, the DEConv integrates prior information into normal convolutionlayer to enhance the representation and generalization capacity. Then by usingthe re-parameterization technique, DEConv is equivalently converted into avanilla convolution with NO extra parameters and computational cost. Byassigning unique spatial importance map (SIM) to every channel, CGA can attendmore useful information encoded in features. In addition, a CGA-based mixupfusion scheme is presented to effectively fuse the features and aid thegradient flow. By combining above mentioned components, we propose ourdetail-enhanced attention network (DEA-Net) for recovering high-qualityhaze-free images. Extensive experimental results demonstrate the effectivenessof our DEA-Net, outperforming the state-of-the-art (SOTA) methods by boostingthe PSNR index over 41 dB with only 3.653 M parameters. The source code of ourDEA-Net will be made available at https://github.com/cecret3350/DEA-Net.

DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention