国家重点研发计划(2018YFC0808706); 国家自然科学基金(62001059); 陕西省重点研发计划(2021GY-019)
针对当前去雾方法存在雾残留、颜色失真等问题, 结合生成对抗网络在图像超分辨率重建的优势, 提出基于通道注意力与条件生成对抗网络图像去雾算法(CGAN-ECA). 网络基于编码-解码结构, 生成器设计多尺度残差模块(multi-scale residual block, MRBlk)和高效通道注意力模块(efficient channel attention, ECA)扩大感受野, 提取多尺度特征, 动态调整不同通道权重, 提高特征利用率. 使用马尔可夫判别器分块评价图像, 提高图像判别准确率. 损失函数增加内容损失, 减少去雾图像的像素和特征级损失, 保留图像更多的细节信息, 实现高质量的图像去雾. 在公开数据集RESIDE实验结果表明, 提出的模型相比于DCP、AOD-Net、DehazeNet和GCANet方法峰值信噪比和结构相似性分别平均提高36.36%, 8.80%, 改善了颜色失真和去雾不彻底的现象, 是一种有效的图像去雾算法.
In terms of the problems such as haze residues and color distortion in existing dehazing methods, this study takes advantage of a generative adversarial network in reconstructing image super-resolution and proposes an image dehazing algorithm based on channel attention and conditional generative adversarial network (CGAN-ECA). Specifically, the network is based on the encoder-decoder structure. The generator is designed with the multi-scale residual block (MRBlk) and efficient channel attention (ECA) to expand the receptive field, extract multi-scale features, dynamically adjust the weights of different channels, and improve the utilization rate of features. In addition, the Markovian discriminator (PatchGAN) is used to evaluate images and improve the accuracy in identifying images. At the same time, a content loss is added into the loss function to reduce pixel-level and feature-level losses of dehazing images, retain more image details, and achieve high-quality image dehazing. The test results based on the public dataset RESIDE show that compared with DCP, AOD-Net, DehazeNet, and GCANet models, the proposed model increases the peak signal to noise ratio (PSNR) and the structural similarity index (SSIM) by 36.36% and 8.80%, respectively, and color distortion and haze residue are solved. Therefore, CGAN-ECA is an effective method for image dehazing.