Global Sensing and Measurements Reuse for Image Compressed Sensing

TL;DR

This paper introduces MR-CCSNet, a deep learning-based image compressed sensing model that reuses measurements across multiple scales and features, leading to improved reconstruction quality and efficiency.

Contribution

The paper proposes a novel network with global sensing and measurement reuse modules to leverage multi-level features and multiple measurement uses for better image reconstruction.

Findings

Significantly outperforms state-of-the-art methods on benchmark datasets.

Effectively utilizes multi-scale features for improved sensing.

Reuses measurements multiple times to extract richer information.

Abstract

Recently, deep network-based image compressed sensing methods achieved high reconstruction quality and reduced computational overhead compared with traditional methods. However, existing methods obtain measurements only from partial features in the network and use them only once for image reconstruction. They ignore there are low, mid, and high-level features in the network\cite{zeiler2014visualizing} and all of them are essential for high-quality reconstruction. Moreover, using measurements only once may not be enough for extracting richer information from measurements. To address these issues, we propose a novel Measurements Reuse Convolutional Compressed Sensing Network (MR-CCSNet) which employs Global Sensing Module (GSM) to collect all level features for achieving an efficient sensing and Measurements Reuse Block (MRB) to reuse measurements multiple times on multi-scale. Finally, experimental results on three benchmark datasets show that our model can significantly outperform state-of-the-art methods.