Image Deblurring and Super-resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

TL;DR

This paper introduces an adaptive sparse domain selection and regularization framework for image deblurring and super-resolution, significantly improving restoration quality by customizing the sparse representation to local image content.

Contribution

It proposes a novel adaptive method that learns multiple sparse bases and regularization models from datasets, selecting the best for each image patch to enhance restoration performance.

Findings

Achieves higher PSNR than state-of-the-art methods.

Improves visual quality of restored images.

Effectively adapts to diverse image contents.

Abstract

As a powerful statistical image modeling technique, sparse representation has been successfully used in various image restoration applications. The success of sparse representation owes to the development of l1-norm optimization techniques, and the fact that natural images are intrinsically sparse in some domain. The image restoration quality largely depends on whether the employed sparse domain can represent well the underlying image. Considering that the contents can vary significantly across different images or different patches in a single image, we propose to learn various sets of bases from a pre-collected dataset of example image patches, and then for a given patch to be processed, one set of bases are adaptively selected to characterize the local sparse domain. We further introduce two adaptive regularization terms into the sparse representation framework. First, a set of autoregressive (AR) models are learned from the dataset of example image patches. The best fitted AR models to a given patch are adaptively selected to regularize the image local structures. Second, the image non-local self-similarity is introduced as another regularization term. In addition, the sparsity regularization parameter is adaptively estimated for better image restoration performance. Extensive experiments on image deblurring and super-resolution validate that by using adaptive sparse domain selection and adaptive regularization, the proposed method achieves much better results than many state-of-the-art algorithms in terms of both PSNR and visual perception.