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

TL;DR

FWB-Net introduces a novel approach combining a non-homogeneous atmospheric scattering model and a front white balance module to effectively reduce color shift in single image dehazing, outperforming existing methods.

Contribution

The paper proposes a new NH-ASM model and a U-Net based front white balance module with a dedicated loss, enhancing dehazing accuracy and color fidelity in complex illumination conditions.

Findings

Outperforms existing dehazing methods on synthetic images

Effectively reduces color shift in real-world hazy images

Demonstrates superior visual quality and color accuracy

Abstract

In recent years, single image dehazing deep models based on Atmospheric Scattering Model (ASM) have achieved remarkable results. But the dehazing outputs of those models suffer from color shift. Analyzing the ASM model shows that the atmospheric light factor (ALF) is set as a scalar which indicates ALF is constant for whole image. However, for images taken in real-world, the illumination is not uniformly distributed over whole image which brings model mismatch and possibly results in color shift of the deep models using ASM. Bearing this in mind, in this study, first, a new non-homogeneous atmospheric scattering model (NH-ASM) is proposed for improving image modeling of hazy images taken under complex illumination conditions. Second, a new U-Net based front white balance module (FWB-Module) is dedicatedly designed to correct color shift before generating dehazing result via atmospheric light estimation. Third, a new FWB loss is innovatively developed for training FWB-Module, which imposes penalty on color shift. In the end, based on NH-ASM and front white balance technology, an end-to-end CNN-based color-shift-restraining dehazing network is developed, termed as FWB-Net. Experimental results demonstrate the effectiveness and superiority of our proposed FWB-Net for dehazing on both synthetic and real-world images.