Toward Convolutional Blind Denoising of Real Photographs

Despite their success in Gaussian denoising, deep convolutional neural networks (CNNs) are still very limited on real noisy photographs, and may even perform worse than the representative traditional methods such as BM3D and K-SVD. In order to improve the robustness and practicability of deep denoising models, this paper presents a convolutional blind denoising network (CBDNet) by incorporating network architecture, noise modeling, and asymmetric learning. Our CBDNet is comprised of a noise estimation subnetwork and a denoising subnetwork, and is trained using a more realistic noise model by considering both signal-dependent noise and in-camera processing pipeline. Motivated by the asymmetric sensitivity of non-blind denoisers (e.g., BM3D) to noise estimation error, the asymmetric learning is presented on the noise estimation subnetwork to suppress more on under-estimation of noise level. To make the learned model applicable to real photographs, both synthetic images based on realistic noise model and real noisy photographs with nearly noise-free images are incorporated to train our CBDNet. The results on three datasets of real noisy photographs clearly demonstrate the superiority of our CBDNet over the state-of-the-art denoisers in terms of quantitative metrics and visual quality. The code and models will be publicly available at https://github.com/GuoShi28/CBDNet.