Group-based Sparse Representation for Image Restoration

TL;DR

This paper introduces a novel group-based sparse representation model for image restoration that captures local and nonlocal image features efficiently, outperforming existing methods in quality and computational complexity.

Contribution

The paper proposes a new group-based sparse representation framework with a self-adaptive dictionary learning method and an efficient split Bregman algorithm for improved image restoration.

Findings

Outperforms state-of-the-art methods in PSNR and visual quality.

Effectively models local sparsity and nonlocal self-similarity.

Reduces computational complexity compared to traditional patch-based methods.

Abstract

Traditional patch-based sparse representation modeling of natural images usually suffer from two problems. First, it has to solve a large-scale optimization problem with high computational complexity in dictionary learning. Second, each patch is considered independently in dictionary learning and sparse coding, which ignores the relationship among patches, resulting in inaccurate sparse coding coefficients. In this paper, instead of using patch as the basic unit of sparse representation, we exploit the concept of group as the basic unit of sparse representation, which is composed of nonlocal patches with similar structures, and establish a novel sparse representation modeling of natural images, called group-based sparse representation (GSR). The proposed GSR is able to sparsely represent natural images in the domain of group, which enforces the intrinsic local sparsity and nonlocal self-similarity of images simultaneously in a unified framework. Moreover, an effective self-adaptive dictionary learning method for each group with low complexity is designed, rather than dictionary learning from natural images. To make GSR tractable and robust, a split Bregman based technique is developed to solve the proposed GSR-driven minimization problem for image restoration efficiently. Extensive experiments on image inpainting, image deblurring and image compressive sensing recovery manifest that the proposed GSR modeling outperforms many current state-of-the-art schemes in both PSNR and visual perception.