Convolutional Neural Networks for Image Denoising and Restoration

Abstract

With the tremendous progress of convolutional neural networks (CNNs) , recent years have witnessed a dramatic upsurge of exploiting CNN toward solving image denoising. Compared to traditional model-based methods, CNN enjoys the principal merits of fast inference and good performance. In this chapter, brief survey and discussions are also given to CNN-based denoising methods from the aspects of effectiveness, interpretability, modeling ability, efficiency, flexibility, and applicability. Then, we provide a gentle introduction of CNN-based denoising methods by presenting and answering the following three questions: (i) can we learn a deep CNN for effective image denoising, (ii) can we learn a single CNN for fast and flexible non-blind image denoising, and (iii) can we leverage CNN denoiser prior to versatile image restoration tasks. Finally, we point out that image denoising remains far from solved. The real image noise is much more sophisticated than additive white Gaussian noise, making the existing CNN denoisers generally perform poorly on real noisy images. As a result, it is still very challenging and valuable to study the issues such as noise modeling, acquisition of noisy-clean image pairs and unsupervised CNN learning for real image denoising.