Image restoration via exponential scale mixture‐based simultaneous sparse prior

Abstract

Image prior plays a decisive role in the performance of widely studied model‐based restoration methods. To further improve restoration performance, this paper proposes an exponential scale mixture‐based simultaneous sparse prior (ESM‐SSP) to accurately characterize image prior information. Specifically, first, two structured dictionaries are adaptively learned to explore the local and non‐local sparsity of similar patch groups simultaneously. Then, the exponential scale mixture (ESM) is employed to model simultaneous sparse coefficients. The adoption of ESM enables us to accurately estimate simultaneous sparse coefficients by adaptively adjusting the regularization parameters. With the aid of ESM‐SSP, an effective image restoration algorithm is developed to preserve more image details. Extensive experimental results on image denoising and deblocking demonstrate that compared with many state‐of‐the‐art model‐based methods, the proposed ESM‐SSP‐based restoration algorithm not only has competitive peak signal‐to‐noise ratio, but also produces higher structural similarity index and better visuals. More importantly, the proposed method can also compete favourably with the superior deep learning‐based restoration methods.

Learning the Hybrid Nonlocal Self-Similarity Prior for Image Restoration

“…As described in Section 2, the learned HNSS prior can characterize the common structures and fine-scale details of the given image well. On the other hand, the structural sparse representation has exhibited notable success in many image restoration tasks [1,4,23,24,28,35]. As a result, we incorporate the learned HNSS prior into the structured sparse representation.…”

“…Recently, deep learning has also been adopted to learn image priors in a supervised manner and has spawned promising results in various image restoration applications [17][18][19][20][21][22]. Both the model-based and deep learning-based approaches mentioned above, however, are dedicated to mining the local properties of images, whose performance is restricted by largely neglecting the self-similarity and nonlocal properties of images [1,23,24]. In addition, deep learning methods require a training set consisting of extensive degraded/ high quality image pairs for supervised learning, which renders them difficult to apply or causes undesirable artifacts in some tasks, such as medical imaging and remote sensing [25,26].…”

“…Given the great success of the nonlocal means (NLM) [27] method, a series of NSS prior-based methods have been developed successively and have shown impressive restoration effects. These approaches can be broadly summarized into three clusters, i.e., filter-based methods [27,29,30], patch group-based sparse representation methods [4,23,[31][32][33][34][35][36][37][38], and low-rank approximation-based methods [2,[39][40][41][42][43][44]. Apart from focusing on the internal NSS prior of the corrupted image, some recent approaches have paid attention to exploiting the external NSS prior learned from high-quality natural images [28,45,46].…”

Image restoration with group sparse representation and low‐rank group residual learning

“…Evidence demonstrates that image priors are the foundation for image restoration, including total variation (TV) [5][6][7], sparsity [2,8], low-rank [9][10][11], and deep image prior [12][13][14][15][16][17][18][19][20]. Particularly, sparsity prior is considered as one of the most remarkable for natural images [2,8,[21][22][23][24]. On the basis of the strategies for manipulating sparsity prior, current algorithms are roughly divided into two classes, that is, patch- [2,25,26] and group-based approaches [8,22,[27][28][29], where the former ones independently perform image restoration for each patch, and the latter ones execute restoration task for each group of patches.…”