COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing

TL;DR

COAST is a deep learning model for compressive sensing that can handle arbitrary sampling matrices with a single trained model, offering interpretability, efficiency, and state-of-the-art performance across diverse sampling scenarios.

Contribution

The paper introduces COAST, a novel deep unfolding network that enables arbitrary sampling in compressive sensing with one model, incorporating RPA, CPMM, and PnP-D modules.

Findings

Handles arbitrary sampling matrices with one model

Achieves state-of-the-art performance on benchmarks

Operates with fast speed

Abstract

Recent deep network-based compressive sensing (CS) methods have achieved great success. However, most of them regard different sampling matrices as different independent tasks and need to train a specific model for each target sampling matrix. Such practices give rise to inefficiency in computing and suffer from poor generalization ability. In this paper, we propose a novel COntrollable Arbitrary-Sampling neTwork, dubbed COAST, to solve CS problems of arbitrary-sampling matrices (including unseen sampling matrices) with one single model. Under the optimization-inspired deep unfolding framework, our COAST exhibits good interpretability. In COAST, a random projection augmentation (RPA) strategy is proposed to promote the training diversity in the sampling space to enable arbitrary sampling, and a controllable proximal mapping module (CPMM) and a plug-and-play deblocking (PnP-D) strategy are further developed to dynamically modulate the network features and effectively eliminate the blocking artifacts, respectively. Extensive experiments on widely used benchmark datasets demonstrate that our proposed COAST is not only able to handle arbitrary sampling matrices with one single model but also to achieve state-of-the-art performance with fast speed. The source code is available on https://github.com/jianzhangcs/COAST.