DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention

Abstract

Single image dehazing is a challenging ill-posed problem which estimates latent haze-free images from observed hazy images. Some existing deep learning based methods are devoted to improving the model performance via increasing 41 the depth or width of convolution. The learning ability of 40 convolutional neural network (CNN) structure is still under- explored. In this paper, a detail-enhanced attention block (DEAB) 39 consisting of the detail-enhanced convolution (DEConv) and the 38 content-guided attention (CGA) is proposed to boost the feature learning for improving the dehazing performance. Specifically, 37 the DEConv integrates prior information into normal convolution 36 layer to enhance the representation and generalization capacity. Then by using the re-parameterization technique, DEConv is 35 equivalently converted into a vanilla convolution with NO extra parameters and computational cost. By assigning unique spatial importance map (SIM) to every channel, CGA can attend more 33 useful information encoded in features. In addition, a CGA- based mixup fusion scheme is presented to effectively fuse the features and aid the gradient flow. By combining above 101 102 Small + Paramerters (M) , La(ge mentioned components, we propose our detail-enhanced attention
network (DEA-Net) for recovering high-quality haze-free images. Extensive experimental results demonstrate the effectiveness of
our DEA-Net, outperforming the state-of-the-art (SOTA) methods by boosting the PSNR index over 41 dB with only 3.653 M
parameters. The source code of our DEA-Net will be made available at https://github.com/cecret3350/DEA-Net.