Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising
This addresses image denoising for computer vision applications, but it is incremental as it modularly integrates existing methods.
The paper tackled image denoising by combining a convolutional neural network (CNN) with a nonlocal filter, achieving state-of-the-art performance on large grayscale image datasets.
We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlocal denoising based on a nonlocal filter (NLF) exploiting the mutual similarities between groups of patches. CNN models are leveraged with noise levels that progressively decrease at every iteration of our framework, while their output is regularized by a nonlocal prior implicit within the NLF. Unlike complicated neural networks that embed the nonlocality prior within the layers of the network, our framework is modular, it uses standard pre-trained CNNs together with standard nonlocal filters. An instance of the proposed framework, called NN3D, is evaluated over large grayscale image datasets showing state-of-the-art performance.