Plug-and-Play Image Restoration with Deep Denoiser Prior

TL;DR

This paper introduces a deep neural network-based denoiser as a prior in plug-and-play image restoration, significantly improving performance across various inverse image problems by combining model-based and learning-based advantages.

Contribution

It develops a highly effective deep CNN denoiser and integrates it into a plug-and-play framework, setting a new benchmark for image restoration tasks.

Findings

Outperforms state-of-the-art model-based methods

Achieves competitive results with learning-based methods

Demonstrates effectiveness on deblurring, super-resolution, and demosaicing

Abstract

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at https://github.com/cszn/DPIR.