[论文解读] Blind Compressed Sensing Over a Structured Union of Subspaces

Jorge G. Silva, Minhua Chen+3 more|arXiv (Cornell University)|Mar 12, 2011

Sparse and Compressive Sensing Techniques参考文献 12被引用 23

一句话总结

该论文提出了一种盲压缩感知框架，用于在单一分块稀疏模型下，从压缩测量中同时进行字典学习与信号恢复，利用多个感知矩阵和低秩矩阵补全理论。证明了当测量值和信号数量充足时，字典和信号可以以高概率唯一恢复（至分块排列和可逆变换为止）。同时提出了一种收敛的交替最小二乘算法，并在图像修复任务中验证，取得了当前最先进的PSNR结果。

ABSTRACT

This paper addresses the problem of simultaneous signal recovery and dictionary learning based on compressive measurements. Multiple signals are analyzed jointly, with multiple sensing matrices, under the assumption that the unknown signals come from a union of a small number of disjoint subspaces. This problem is important, for instance, in image inpainting applications, in which the multiple signals are constituted by (incomplete) image patches taken from the overall image. This work extends standard dictionary learning and block-sparse dictionary optimization, by considering compressive measurements, e.g., incomplete data). Previous work on blind compressed sensing is also generalized by using multiple sensing matrices and relaxing some of the restrictions on the learned dictionary. Drawing on results developed in the context of matrix completion, it is proven that both the dictionary and signals can be recovered with high probability from compressed measurements. The solution is unique up to block permutations and invertible linear transformations of the dictionary atoms. The recovery is contingent on the number of measurements per signal and the number of signals being sufficiently large; bounds are derived for these quantities. In addition, this paper presents a computationally practical algorithm that performs dictionary learning and signal recovery, and establishes conditions for its convergence to a local optimum. Experimental results for image inpainting demonstrate the capabilities of the method.

研究动机与目标

• 解决在无法获得完整信号观测的情况下，从压缩测量中恢复信号并学习字典的挑战。
• 将字典学习与分块稀疏字典优化推广至存在不完整数据的压缩感知框架。
• 通过引入多个感知矩阵并放宽对学习字典的约束，推广盲压缩感知方法。
• 建立在压缩测量下唯一恢复字典和信号的理论条件。
• 开发一种实用且收敛的联合字典学习与信号恢复算法，适用于压缩感知场景。

提出的方法

• 将信号建模为在未知字典上的单一分块稀疏表示，假设其位于由分块结构定义的子空间并集中。
• 利用多个感知矩阵，通过低秩矩阵补全理论实现恢复，利用系数矩阵的结构化稀疏性。
• 采用交替最小二乘算法，迭代更新字典和稀疏系数，在较弱条件下具备收敛性保证。
• 通过将重叠图像块视为信号，应用该方法于图像修复，利用块平均实现重建。
• 推导出每信号所需测量数和实现高概率恢复所需信号数的理论边界。
• 利用矩阵补全结果证明，解在分块排列和字典原子可逆线性变换下唯一。

实验结果

研究问题

• RQ1 当信号为单一分块稀疏时，能否从压缩测量中联合实现字典学习与信号恢复？
• RQ2 在何种条件下，字典和信号可从压缩测量中唯一恢复（至等价类为止）？
• RQ3 多个感知矩阵如何提升盲压缩感知中的恢复性能与理论保证？
• RQ4 在此框架下，实现高概率恢复所需的每信号最小测量数和信号数是多少？
• RQ5 所提出的交替最小二乘算法在实际中表现如何？是否收敛至局部最优？

主要发现

• 该方法在50%像素观测率下实现了高质量图像修复，'Barbara'图像PSNR达27.93 dB，'house'图像PSNR达31.80 dB。
• 相变分析表明，随着观测像素比例增加，重建成功（PSNR > 40 dB）的可能性显著提升，尤其在较大分块尺寸下更明显。
• 通过算法学习到的字典原子捕捉了有意义的图像结构，如衣物纹理和背景，使用相同字典块的相似块具有相似表示。
• 理论边界证实，当每信号的测量数和信号总数足够大时，可高概率实现唯一恢复。
• 交替最小二乘算法在弱条件下收敛至局部最优，且无需参数调优或精细初始化即表现出鲁棒性能。
• 增大最大分块尺寸（$k_{ ext{max}}$）可提升PSNR，表明模型简洁性与重建精度之间存在权衡。