Blind Compressed Sensing Over a Structured Union of Subspaces

TL;DR

This paper introduces a method for simultaneous signal recovery and dictionary learning from compressive measurements, leveraging union of subspaces, with theoretical guarantees and practical algorithms demonstrated on image inpainting tasks.

Contribution

It extends blind compressed sensing to multiple sensing matrices and incomplete data, providing theoretical recovery guarantees and a practical algorithm.

Findings

High-probability recovery of signals and dictionaries from compressed measurements

Theoretical bounds on measurements needed for successful recovery

Effective image inpainting demonstrated with experimental results

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.