Texture-guided CNN for image denoising

Convolutional neural networks (CNNs) can effectively extract structural information in image denoising. However, they tend to ignore texture information. To tackle this problem, we present a texture-guided CNN for image denoising (TDCNN), which depends on blocks for texture extraction, refinement, and transformation to realize excellent denoising performance on both quantitative and visual metrics. A texture-extraction block combines non-local similarity and two sub-networks to extract texture and structural information. A refinement block with a stacked architecture mines accurate information from complementary features. A transformation block is used to obtain clean output images. A joint loss function, including perceptual loss and mean square error, enhances the robustness of the proposed denoiser. Experiments show that the proposed TDCNN is superior to some popular methods for denoising synthetic and real images.