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

In recent years, single image dehazing deep models based on AtmosphericScattering Model (ASM) have achieved remarkable results. But the dehazingoutputs of those models suffer from color shift. Analyzing the ASM model showsthat the atmospheric light factor (ALF) is set as a scalar which indicates ALFis constant for whole image. However, for images taken in real-world, theillumination is not uniformly distributed over whole image which brings modelmismatch and possibly results in color shift of the deep models using ASM.Bearing this in mind, in this study, first, a new non-homogeneous atmosphericscattering model (NH-ASM) is proposed for improving image modeling of hazyimages taken under complex illumination conditions. Second, a new U-Net basedfront white balance module (FWB-Module) is dedicatedly designed to correctcolor shift before generating dehazing result via atmospheric light estimation.Third, a new FWB loss is innovatively developed for training FWB-Module, whichimposes penalty on color shift. In the end, based on NH-ASM and front whitebalance technology, an end-to-end CNN-based color-shift-restraining dehazingnetwork is developed, termed as FWB-Net. Experimental results demonstrate theeffectiveness and superiority of our proposed FWB-Net for dehazing on bothsynthetic and real-world images.

FWB-Net:Front White Balance Network for Color Shift Correction in Single Image Dehazing via Atmospheric Light Estimation