A deep convolutional neural network for salt-and-pepper noise removal using selective convolutional blocks
This addresses a specific image denoising problem for computer vision applications, but is incremental as it adapts CNNs to a less common noise type.
The paper tackled salt-and-pepper noise removal in images by proposing SeConvNet, a deep CNN with selective convolutional blocks, which outperformed state-of-the-art methods, especially at high noise densities.
In recent years, there has been an unprecedented upsurge in applying deep learning approaches, specifically convolutional neural networks (CNNs), to solve image denoising problems, owing to their superior performance. However, CNNs mostly rely on Gaussian noise, and there is a conspicuous lack of exploiting CNNs for salt-and-pepper (SAP) noise reduction. In this paper, we proposed a deep CNN model, namely SeConvNet, to suppress SAP noise in gray-scale and color images. To meet this objective, we introduce a new selective convolutional (SeConv) block. SeConvNet is compared to state-of-the-art SAP denoising methods using extensive experiments on various common datasets. The results illustrate that the proposed SeConvNet model effectively restores images corrupted by SAP noise and surpasses all its counterparts at both quantitative criteria and visual effects, especially at high and very high noise densities.