KRNET: Image Denoising with Kernel Regulation Network
This work addresses the challenge of effective denoising for multi-channel color images, which is important for applications in photography and computer vision, representing an incremental improvement over prior CNN methods.
The paper tackled the problem of low performance in multi-channel color image denoising with existing CNN-based methods by proposing KRNET, a deep CNN-based denoiser with a kernel regulation module, which achieved significant performance gains over state-of-the-art methods across various noise levels.
One popular strategy for image denoising is to design a generalized regularization term that is capable of exploring the implicit prior underlying data observation. Convolutional neural networks (CNN) have shown the powerful capability to learn image prior information through a stack of layers defined by a combination of kernels (filters) on the input. However, existing CNN-based methods mainly focus on synthetic gray-scale images. These methods still exhibit low performance when tackling multi-channel color image denoising. In this paper, we optimize CNN regularization capability by developing a kernel regulation module. In particular, we propose a kernel regulation network-block, referred to as KR-block, by integrating the merits of both large and small kernels, that can effectively estimate features in solving image denoising. We build a deep CNN-based denoiser, referred to as KRNET, via concatenating multiple KR-blocks. We evaluate KRNET on additive white Gaussian noise (AWGN), multi-channel (MC) noise, and realistic noise, where KRNET obtains significant performance gains over state-of-the-art methods across a wide spectrum of noise levels.