论文标题
多阶段图像通过小波变换降级
Multi-stage image denoising with the wavelet transform
论文作者
论文摘要
深度卷积神经网络（CNN）用于图像通过自动挖掘精确的结构信息进行图像。但是，大多数现有的CNN依赖于扩大设计网络的深度以获得更好的降级性能，这可能会导致训练难度。在本文中，我们通过三个阶段，即动态卷积块（DCB），两个级联的小波变换和增强块（网站）（网站）和一个残留块（RB）提出了具有小波变换（MWDCNN）的多阶段图像。 DCB使用动态卷积来动态调整几次卷积的参数，以在降级性能和计算成本之间做出权衡。 Web结合了信号处理技术（即小波转换）和歧视性学习的组合，以抑制噪声，以恢复图像DeNoising中更详细的信息。为了进一步删除冗余功能，RB用于完善获得的功能，以改善通过改进残留密度架构来重建清洁图像的特征。实验结果表明，在定量和定性分析方面，提出的MWDCNN优于一些流行的denoising方法。代码可在https://github.com/hellloxiaotian/mwdcnn上找到。
Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. However, most of existing CNNs depend on enlarging depth of designed networks to obtain better denoising performance, which may cause training difficulty. In this paper, we propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and a residual block (RB). DCB uses a dynamic convolution to dynamically adjust parameters of several convolutions for making a tradeoff between denoising performance and computational costs. WEB uses a combination of signal processing technique (i.e., wavelet transformation) and discriminative learning to suppress noise for recovering more detailed information in image denoising. To further remove redundant features, RB is used to refine obtained features for improving denoising effects and reconstruct clean images via improved residual dense architectures. Experimental results show that the proposed MWDCNN outperforms some popular denoising methods in terms of quantitative and qualitative analysis. Codes are available at https://github.com/hellloxiaotian/MWDCNN.
