Content-aware Scalable Deep Compressed Sensing

TL;DR

CASNet is a novel content-aware scalable deep network for image compressed sensing that adaptively allocates sampling rates, reconstructs high-quality images, and is efficient and robust through innovative strategies.

Contribution

The paper introduces CASNet, a unified deep network with saliency-based sampling, a learnable sampling matrix, and end-to-end training for scalable image compressed sensing.

Findings

CASNet outperforms existing CS networks significantly.

The saliency-based sampling improves reconstruction quality.

The proposed strategies enhance training efficiency and robustness.

Abstract

To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction. We first adopt a data-driven saliency detector to evaluate the importances of different image regions and propose a saliency-based block ratio aggregation (BRA) strategy for sampling rate allocation. A unified learnable generating matrix is then developed to produce sampling matrix of any CS ratio with an ordered structure. Being equipped with the optimization-inspired recovery subnet guided by saliency information and a multi-block training scheme preventing blocking artifacts, CASNet jointly reconstructs the image blocks sampled at various sampling rates with one single model. To accelerate training convergence and improve network robustness, we propose an SVD-based initialization scheme and a random transformation enhancement (RTE) strategy, which are extensible without introducing extra parameters. All the CASNet components can be combined and learned end-to-end. We further provide a four-stage implementation for evaluation and practical deployments. Experiments demonstrate that CASNet outperforms other CS networks by a large margin, validating the collaboration and mutual supports among its components and strategies. Codes are available at https://github.com/Guaishou74851/CASNet.