记笔记

Image Dehazing Using Conditional Patch Generative Adversarial Network

Changyou ShiJianping LuQiang SunJing ZhouRongze XiaWei Huang

College of Communication NCOs,Army Engineering University of PLA

摘要：*Restoring clear images from hazy images is an ill-posed problem and most recent researches based on atmospheric scattering model are not work well when facing real fog pictures. We propose an algorithm based on the Conditional Generative Adversarial Network（CGAN）, which is an end-to-end training network that outputs the dehazing results directly. The generator is designed as a skip connection U-Net structure, so that it can generate better results.We further modify the basic CGAN formulation by introducing the gradient loss, features loss, reconstruction loss. Instead of scalar loss, a patch-GAN loss is used to regularize the network model.Haze4 K and STOS datasets are used to train and evaluate the network. The experimental results show that the algorithm performs competitive result and better generality against the other works.

关键词：

Image dehazing; Computer version; Conditional generative adversarial network; Convolutional neural network;

会议名称：

2021年第四届算法、计算和人工智能国际会议

会议时间：

2021-12-22

会议地点：

中国海南三亚