Litcius/Paper detail

Exploring Fuzzy Priors From Multimapping GAN for Robust Image Dehazing

Shengdong Zhang, Xiaoqin Zhang, Wenqi Ren, Li Zhao, En Fan, Feng Huang

2025IEEE Transactions on Fuzzy Systems12 citationsDOI

Abstract

Single image dehazing has been extensively studied. While convolutional neural networks (CNNs) have driven notable progress in single image dehazing, their performance remains fundamentally constrained by the limited local receptive fields of convolutional operations, which impede the capture of global structural dependencies. In contrast, generative adversarial networks (GANs) have demonstrated exceptional capabilities in image synthesis, offering global insights into structure, texture, and color. The fuzzy prior, a probabilistic knowledge acquired through adversarial training in GANs, plays a pivotal role in robust dehazing. Motivated by this, we propose the fuzzy prior guided dehazing network (FPGDN). Our framework begins with a novel module that distills the fuzzy prior by translating an edge map into a color image, simultaneously capturing global structural, local textural, and color information. Subsequently, a dehazing network is constructed, leveraging this fuzzy prior. While the fuzzy prior captures rich color and texture features, the generated images may exhibit color shifts relative to the original scene. To remedy this, a CNN network is employed to capture local nuances and refine the dehazing outcome. Extensive experiments substantiate that the proposed FPGDN achieves superior dehazing performance on a variety of real and synthetic hazy images.

Topics & Concepts

Computer scienceArtificial intelligenceFuzzy logicConvolutional neural networkProbabilistic logicComputer visionPrior probabilityImage (mathematics)Pattern recognition (psychology)Image restorationEnhanced Data Rates for GSM EvolutionGenerative adversarial networkPixelAdversarial systemArtificial neural networkFuzzy setImage segmentationImage processingIterative reconstructionColor imageContextual image classificationImage Enhancement TechniquesMedical Image Segmentation TechniquesImage and Signal Denoising Methods