CVMar 29, 2019

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

arXiv:1903.12529v1397 citations
Originality Incremental advance
AI Analysis

This addresses a fundamental challenge in image processing for applications requiring super-resolution from blurry inputs, though it is incremental as it extends existing plug-and-play methods.

The paper tackles the problem of single image super-resolution for low-resolution images with arbitrary blur kernels, proposing a deep plug-and-play framework that integrates blur kernel estimation and achieves effective results on synthetic and real images.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes