Robust Image Denoising with Texture-Aware Neural Network

Bo Fu, Liyan Wang, Zhongxuan Luo

Abstract: Image denoising is a well-studied yet still hot research topic in the image processing community. Recently, image denoising with deep neural networks has achieved superior performance, however they can not recover tiny details from noisy images. Motivated by this problem, we propose a Texture-Aware Neural Network named TANet, which is composed of main network part with attention mechanism, residual structure and Texture-Aware Modular. Proposed Texture-Aware Modular owns dual paths, denoised image from main denoising network and clean image are input different path respectively. From Texture-Aware Modular, we get two sets intermediate codes and calculate corresponding perceptual loss. This perceptual loss is designed to generate auxiliary super-vision for tiny detail recovery from mixed residual details and noise set. Extensive experimental results demonstrate that the proposed TANet is on a par with the state-of-the-art denoising methods.