Multi-stage image denoising with the wavelet transform

Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining ac-curate 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 im-ages 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.(c) 2022 Elsevier Ltd. All rights reserved.

Automated summary

This paper proposes a multi-stage image denoising CNN with wavelet transform, using dynamic convolution, wavelet transform and enhancement, and residual block to improve denoising performance. Experimental results show that the proposed method outperforms popular denoising methods.