Retrieval Compensated Group Structured Sparsity for Image Super-Resolution
Retrieval Compensated Group Structured Sparsity for Image Super-Resolution
复制标题
图像超分辨率的检索补偿组结构化稀疏性
DOI：
10.1109/tmm.2016.2614427
复制
发表时间：
2017-02-01
影响因子：
7.3
通讯作者：
Guo, Zongming
中科院分区：
文献类型：
--
作者：
Liu, Jiaying;Yang, Wenhan;Guo, Zongming
基于稀疏表示的图像超分辨率是一个很好的研究课题，然而，一个通用的稀疏框架，可以利用内部和外部的依赖关系仍然没有探索。在本文中，我们提出了一个组结构的稀疏表示方法，充分利用内部和外部的依赖关系，以促进图像超分辨率。通过两阶段检索和细化引入外部补偿相关信息。首先，在全局阶段，利用基于内容的特征来选择相关的外部图像。然后，在局部阶段，补丁的相似性，衡量的内容和高频补丁功能的组合，被用来细化所选择的外部数据。为了更好地从基于内部数据分布的补偿后的外部数据中学习先验知识并进一步补充它们的优势，将非局部冗余引入稀疏表示模型，形成基于自适应结构化字典的组稀疏框架。我们提出的自适应结构化字典由两部分组成：一部分在内部数据上训练，另一部分在补偿的外部数据上训练。两者都以集群形式组织。为了提供所需的过完备性，当稀疏编码一个给定的LR补丁，所提出的结构化字典动态生成的补丁，而不是只选择最近的一个，在以前的方法中，通过组合几个最近的内部和外部正交子字典。大量的图像超分辨率实验验证了该方法的有效性和最先进的性能。对污染和不相关外部数据的额外实验也证明了其上级鲁棒性。
Sparse representation-based image super-resolution is a well-studied topic; however, a general sparse framework that can utilize both internal and external dependencies remains unexplored. In this paper, we propose a group-structured sparse representation approach to make full use of both internal and external dependencies to facilitate image super-resolution. External compensated correlated information is introduced by a two-stage retrieval and refinement. First, in the global stage, the content-based features are exploited to select correlated external images. Then, in the local stage, the patch similarity, measured by the combination of content and high-frequency patch features, is utilized to refine the selected external data. To better learn priors from the compensated external data based on the distribution of the internal data and further complement their advantages, nonlocal redundancy is incorporated into the sparse representation model to form a group sparsity framework based on an adaptive structured dictionary. Our proposed adaptive structured dictionary consists of two parts: one trained on internal data and the other trained on compensated external data. Both are organized in a cluster-based form. To provide the desired over-completeness property, when sparsely coding a given LR patch, the proposed structured dictionary is generated dynamically by combining several of the nearest internal and external orthogonal subdictionaries to the patch instead of selecting only the nearest one as in previous methods. Extensive experiments on image super-resolution validate the effectiveness and state-of-the-art performance of the proposed method. Additional experiments on contaminated and uncorrelated external data also demonstrate its superior robustness.