KRNET: Image Denoising with Kernel Regulation Network
Abstract
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.
Cite
@article{arxiv.1910.08867,
title = {KRNET: Image Denoising with Kernel Regulation Network},
author = {Peng Liu and Xiaoxiao Zhou and Junyiyang Li and El Basha Mohammad D and Ruogu Fang},
journal= {arXiv preprint arXiv:1910.08867},
year = {2019}
}