Deep Universal Blind Image Denoising

TL;DR

This paper introduces a CNN-based approach for blind image denoising that combines the strengths of traditional priors and deep learning, effectively handling real-world noise with a moderate model size.

Contribution

It proposes a novel CNN architecture that divides the blind denoising task into sub-problems, enabling efficient inference and improved performance on real-world noise.

Findings

Successfully removes blind and real-world noise

Operates with a moderate number of parameters

Leverages both explicit priors and deep learning advantages

Abstract

Image denoising is an essential part of many image processing and computer vision tasks due to inevitable noise corruption during image acquisition. Traditionally, many researchers have investigated image priors for the denoising, within the Bayesian perspective based on image properties and statistics. Recently, deep convolutional neural networks (CNNs) have shown great success in image denoising by incorporating large-scale synthetic datasets. However, they both have pros and cons. While the deep CNNs are powerful for removing the noise with known statistics, they tend to lack flexibility and practicality for the blind and real-world noise. Moreover, they cannot easily employ explicit priors. On the other hand, traditional non-learning methods can involve explicit image priors, but they require considerable computation time and cannot exploit large-scale external datasets. In this paper, we present a CNN-based method that leverages the advantages of both methods based on the Bayesian perspective. Concretely, we divide the blind image denoising problem into sub-problems and conquer each inference problem separately. As the CNN is a powerful tool for inference, our method is rooted in CNNs and propose a novel design of network for efficient inference. With our proposed method, we can successfully remove blind and real-world noise, with a moderate number of parameters of universal CNN.