摘要
雾天拍摄的图片存在颜色失真、细节模糊等问题,会对图片的质量造成一定影响。许多基于深度学习的方法虽然在去除合成的均匀雾霾图片上具有很好的效果,但在最新的NTIRE挑战赛中引入的真实非均匀去雾数据集上效果较差。主要原因是非均匀雾霾的分布较复杂,纹理细节在去雾过程中很容易丢失,并且该数据集的样本数量有限,容易产生过拟合。因此提出了一种双分支生成器的条件生成对抗网络(DB-CGAN)。其中,一条分支以U-net为基础架构,通过“加强-整合-减去”的策略在解码器中加入增强模块,从而增强解码器中特征的恢复,并使用密集特征融合为非相邻层级建立足够的连接。另一分支使用多层残差的结构来加快网络的训练,并串联大量的通道注意力模块,以最大限度地提取更多的高频细节特征。最后,使用一个简单有效的融合子网来融合两个分支。在实验中,所提模型在评价指标峰值信噪比(PSNR)和结构相似性(SSIM)上明显优于先前的暗通道先验(DCP)、一体化去雾网络(AODNet)、门控上下文聚合网络(GCANet)、多尺度增强去雾网络(MSBDN)去雾模型。实验结果表明,所提出的网络能够在非均匀去雾数据集上具有更好的性能。
The pictures taken on hazy days have color distortion and blurry details,which will affect the quality of the pictures to a certain extent.Many deep learning based methods have good results on synthetic homogeneous haze images,but they have poor results on the real nonhomogeneous dehazing dataset introduced in the latest NTIRE(New Trends in Image Restoration and Enhancement)challenge.The main reason is that the non-uniform distribution of haze is complicated,and the texture details are easily lost in the process of dehazing.Moreover,the sample number of this dataset is limited,which is easy to lead to overfitting.Therefore,a Conditional Generative Adversarial Network with Dual-Branch generators(DBCGAN)was proposed.Among them,in one branch,with U-net used as the basic architecture,through the strategy of"Strengthen-Operate-Subtract",enhancement modules were added to the decoder to enhance the recovery of features in the decoder,and the dense feature fusion was used to build enough connections for non-adjacent levels.In the other branch,a multi-layer residual structure was used to speed up the training of the network,and a large number of channel attention modules were concatenated to extract more high-frequency detailed features as many as possible.Finally,a simple and efficient fusion subnet was used to fuse the two branches.In the experiment,this model is significantly better than the previous Dark Channel Prior(DCP),All-in-One Dehazing Network(AODNet),Gated Context Aggregation Network(GCANet),and Multi-Scale Boosted Dehazing Network(MSBDN)dehazing models in the evaluation index Peak Signal-toNoise Ratio(PSNR)and Structural SIMilarity(SSIM).Experimental results show that the proposed network has better performance on nonhomogeneous dehazing datasets.
作者
朱利安
张鸿
ZHU Li’an;ZHANG Hong(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan Hubei 430065,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System(Wuhan University of Science and Technology),Wuhan Hubei 430065,China)
出处
《计算机应用》
CSCD
北大核心
2023年第2期567-574,共8页
journal of Computer Applications
关键词
深度学习
非均匀图像去雾
生成对抗网络
增强U-net
通道注意力
deep learning
nonhomogeneous image dehazing
Generative Adversarial Network(GAN)
enhanced U-net
channel attention
