A learning-based method for compressive image recovery
A learning-based method for compressive image recovery
复制标题
一种基于学习的压缩图像恢复方法
DOI：
10.1016/j.jvcir.2013.06.019
复制
发表时间：
2013-10-01
影响因子：
2.6
通讯作者：
Zhang, Lei
中科院分区：
文献类型：
--
作者：
Dong, Weisheng;Shi, Guangming;Zhang, Lei
压缩感知（CS）理论指出，稀疏信号可以从一些随机测量重建。压缩图像恢复（CIR）的一个重要问题是最佳稀疏空间通常是未知的和/或对于非平稳信号（例如，自然图像）。在本文中，除了固定的稀疏空间，先验模型，特别是一组分段自回归（AR）模型，编码的图像微结构的共同统计，从示例图像补丁学习，然后使用它们来构建自适应稀疏正则化CIR。此外，一个互补的非局部结构稀疏正则化也被纳入到CIR过程，以提高鲁棒性。局部AR模型和非局部冗余的正则化使得所提出的CIR非常有效。在基准图像上的实验结果表明，该算法在PSNR和视觉质量方面都明显优于以往的CIR方法。(C)2013 Elsevier Inc. All rights reserved.
Compressive sensing (CS) theory dictates that a sparse signal can be reconstructed from a few random measurements. An important issue of compressive image recovery (CIR) is that the optimal sparse space is usually unknown and/or it often varies spatially for non-stationary signals (e.g., natural images). In this paper, apart from fixed sparse spaces, prior models, specifically a set of piecewise autoregressive (AR) models that encode the common statistics of image micro-structures, are learned from example image patches, and they are then used to construct adaptive sparsity regularizers for CIR. Furthermore, a complementary non-local structural sparsity regularizer is also incorporated into the CIR process to improve the robustness. The regularization by local AR model and non-local redundancy makes the proposed CIR very effective. Experimental results on benchmark images validate that the proposed algorithm can outperform significantly previous CIR methods in terms of both PSNR and visual quality. (C) 2013 Elsevier Inc. All rights reserved.