Deep Learning Sparse Ternary Projections for Compressed Sensing of Images

TL;DR

This paper introduces a deep learning method to generate sparse ternary projection matrices for compressed sensing, enabling efficient image reconstruction with reduced complexity compared to traditional Gaussian projections.

Contribution

It presents an end-to-end deep learning framework that jointly learns sparse ternary projections and reconstruction operators for improved compressed sensing of images.

Findings

Outperforms state-of-the-art methods in image reconstruction quality.

Achieves significant reduction in computational complexity.

Demonstrates effectiveness on real image datasets.

Abstract

Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guarantees with high probability; however, sparse ternary {0, -1, +1} projections are more suitable for hardware implementation. In this paper, we present a deep learning approach to obtain very sparse ternary projections for compressed sensing. Our deep learning architecture jointly learns a pair of a projection matrix and a reconstruction operator in an end-to-end fashion. The experimental results on real images demonstrate the effectiveness of the proposed approach compared to state-of-the-art methods, with significant advantage in terms of complexity.