基于Res2-Unet多阶段监督的图像降噪

Deep learning image denoising based on multi-stage supervised with Res2-Unet

为了提高基于深度学习的图像降噪效率,提出了一种基于Res2-Unet-SE的多阶段监督深度残差(Multi-stage Supervised Deep Residual,MSDR)降噪神经网络。首先基于该神经网络,将图像降噪分为多阶段处理过程;然后在各处理阶段,将不同分辨率图像块输入到Res2-Unet子网络中获取不同尺度特征信息,并通过通道注意力机制将自适应学习的特征融合信息传递到下阶段;最后将不同尺度特征信息叠加,完成高质量的图像降噪。实验选择BSD400数据集用于训练,通过Set12数据集进行高斯噪声的降噪测试;通过SIDD数据集完成真实噪声的降噪测试。通过与常见的降噪神经网络对比表明,对图像添加σ=15,25,50的高斯噪声时,经本文算法降噪后的图像PSNR比对高斯噪声消除性能较好的DNCNN分别提高0.03 dB,0.05 dB,0.14 dB;在σ=25,50时,相较于MPRNET分别提高了0.02 dB, 0.06 dB。对含真实噪声的图像,经本文算法降噪后的图像PSNR比CBDNET算法提高0.48 dB。实验分析表明,本文算法在图像降噪上具有较高的鲁棒性,不仅能从噪声中有效恢复图像细节,还能充分保持图像的全局依赖关系。

To restore high quality images from different types of noise images,this study developed a multi-stage supervised deep residual(MSDR)neural network based on Res2-Unet-SE.First,using the neural network,the image denoising task was devised as a multi-stage process.Then,in each processing stage,image blocks with different resolutions were input into a Res2-Unet sub-network to obtain feature information at different scales,and an adaptive learning of the feature fusion information was transferred to the next stage through a channel attention mechanism.Finally,the feature information of different scales was superimposed to achieve high-quality image noise reduction.The BSD400 dataset was selected for training in the experiments,and a Gaussian noise reduction test was performed using the Set12 data set.Real noise reduction test was conducted using the SIDD data set.Compared with the common denoising neural network,the peak signal-to-noise ratios(PSNRs)of the proposed denoising convolutional neural network(DnCNN)improved by 0.03 dB,0.05 dB,and 0.14 dB when Gaussian noises ofσ=15,25 and 50,respectively,were added to the image data set.Compared with the latest dual residual block net⁃work(DuRN)algorithm,the PSNR of the image denoised using the proposed algorithm was higher by 0.06 dB,0.57 dB,and 0.39 dB,respectively.For images containing real noise,the PSNR of the image denoised by the proposed algorithm was 0.6 dB higher than that by the convolutional blind denoising net⁃work(CBDNET)algorithm.The results indicate that the proposed algorithm is highly robust in the task of image denoising,and it can effectively remove noise and restore the details of an image,as well as fully maintain the global dependence of the image.