Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels

TL;DR

This paper introduces a flexible deep super-resolution framework that extends traditional methods to handle low-resolution images with arbitrary blur kernels by integrating plug-and-play techniques and blur kernel estimation.

Contribution

It presents a novel degradation model and a plug-and-play algorithm that allows the use of various super-resolvers for arbitrary blur kernels, enhancing super-resolution versatility.

Findings

Effective on synthetic and real blurry LR images

Outperforms existing methods in handling arbitrary blur kernels

Flexible framework allowing different super-resolver priors

Abstract

While deep neural networks (DNN) based single image super-resolution (SISR) methods are rapidly gaining popularity, they are mainly designed for the widely-used bicubic degradation, and there still remains the fundamental challenge for them to super-resolve low-resolution (LR) image with arbitrary blur kernels. In the meanwhile, plug-and-play image restoration has been recognized with high flexibility due to its modular structure for easy plug-in of denoiser priors. In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help of plug-and-play framework to handle LR images with arbitrary blur kernels. Specifically, we design a new SISR degradation model so as to take advantage of existing blind deblurring methods for blur kernel estimation. To optimize the new degradation induced energy function, we then derive a plug-and-play algorithm via variable splitting technique, which allows us to plug any super-resolver prior rather than the denoiser prior as a modular part. Quantitative and qualitative evaluations on synthetic and real LR images demonstrate that the proposed deep plug-and-play super-resolution framework is flexible and effective to deal with blurry LR images.