基于层级权值交互和拉普拉斯先验的非均匀去雾

Nonuniform Defogging Based on Hierarchical Weight Interaction and Laplacian Prior

针对非均匀雾霾图像去雾过程中细节丢失和雾霾残留,导致图像质量受损的问题,提出一种基于层级权值交互和拉普拉斯先验的非均匀去雾方法。首先,在基准网络中引入层级权值交互模块,以自适应地调整权值,在不同尺度上对特征图进行加权融合。同时,使用全感受野聚合模块丰富感受野,让模型更全面地理解图像内容信息。然后,引入频域信息分支,使用小波函数将图像分解为低频和高频分量,低频部分包含整体结构信息,高频部分提供局部细节信息,两者共同提高了图像的清晰度。最后,引入拉普拉斯损失重建图像,恢复图像的细节特征,提高生成图像的质量。实验结果表明,相比原始算法,所提算法在4个数据集上的峰值信噪比(PSNR)分别提高了0.8 dB、1.54 dB、1.14 dB和0.23 dB,并在测试集上取得了较优的去雾效果。

This study presents a nonuniform dehazing method based on hierarchical weight interaction and Laplacian prior to address the issues of detail loss and residual haze in nonuniform hazy images,which often result in degraded image quality.First,a hierarchical weight interaction module is introduced in the baseline network to adaptively adjust weights and perform a weighted fusion of feature maps at different scales.Furthermore,a global receptive field aggregation module is introduced to enrich the receptive field,allowing the model to comprehensively understand the content information in the image.Then,a frequency domain information branch is introduced to decompose the image into lowfrequency and highfrequency components using wavelet functions.The lowfrequency component contains global structural information,whereas the highfrequency component provides detailed local information.This decomposition collectively enhances the image clarity.Finally,a Laplacian loss is incorporated to reconstruct the image,effectively restoring its finegrained features and improving the quality of the generated images.Experimental results show that the proposed algorithm achieves superior results on the test set,with an increase in peak signaltonoise ratio(PSNR)by 0.8 dB,1.54 dB,1.14 dB,and 0.23 dB compared with the original algorithm on four datasets.