文献类型：期刊文献

英文题名：GAN-based dehazing network with knowledge transferring

作者：Zhang, Shengdong[1,2];Zhang, Xiaoqin[1];Shen, Linlin[3];Fan, En[2]

机构：[1]Wenzhou Univ, Key Lab Intelligent Informat Safety & Emergency Zh, Wenzhou 325035, Zhejiang, Peoples R China;[2]Shaoxing Univ, Comp Sci Engn Dept, Shaoxing 312000, Zhejiang, Peoples R China;[3]Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Guangdong, Peoples R China

年份：2023

外文期刊名：MULTIMEDIA TOOLS AND APPLICATIONS

收录：SCI-EXPANDED(收录号：WOS:001085957900004)、、WOS

基金：Shengdong Zhang is supported by the National Natural Science Foundation of China (Nos.U2033210, 82261138629, and 62271321). Shengdong Zhang is partially supported by the Science Project of Shaoxing University (Nos. 2022LG006, 20205048, and 20210026), the Science and Technology PlanProject in Basic Public Welfare class of Shaoxing city (No.2022A1)

语种：英文

外文关键词：GAN prior; Dehazing; Real image dehazing; Dense haze

外文摘要：Capturing images under the condition of haze often shows low contrast and fades the color. Restoring the haze-free image from a single image is a challenging task due to the ill-pose of the problem and high degradation. To solve this problem, we propose a GAN (Generative Adversarial Network) Prior Guided Dehazing Network (GPGDN). While the prior dehazing methods often trained the model with adversarial loss to obtain a photorealistic dehazed result, The proposed method explores to transfer of the rich and diverse priors learned from large clean images to dehazing problem. The GPGDN consists of an Encoder and a GAN-based decoder. The Encoder is designed to generate the latent code and noise input, which are fed to GAN-based decoder and generate the final dehazed result. Due to the high degradation of dense haze areas, it is hard to restore high-quality results for these areas. The proposed method can transfer knowledge from the haze-free images into dehazed results and restore high-quality results. The experiment on simulated outdoor hazy images demonstrates that the proposed method outperforms other methods with a significant gap of 3.40dB. Hazy images dehazing by GPGDN show a clear improvement compared to prior methods.