Robust Deep Compressive Sensing with Recurrent-Residual Structural Constraints

TL;DR

This paper introduces R$^2$CS-NET, a deep compressive sensing framework that combines online adaptive optimization with deep learning, achieving robust, efficient, and high-quality image reconstruction, especially for color images.

Contribution

It presents the first deep CS framework integrating adaptive online optimization with deep learning, improving robustness and efficiency over existing methods.

Findings

Outperforms classic LSTM in adaptive latent optimization.

Demonstrates superior robustness and generalization among deep CS benchmarks.

Enables hardware implementation for practical applications.

Abstract

Existing deep compressive sensing (CS) methods either ignore adaptive online optimization or depend on costly iterative optimizer during reconstruction. This work explores a novel image CS framework with recurrent-residual structural constraint, termed as R$^2$CS-NET. The R$^2$CS-NET first progressively optimizes the acquired samplings through a novel recurrent neural network. The cascaded residual convolutional network then fully reconstructs the image from optimized latent representation. As the first deep CS framework efficiently bridging adaptive online optimization, the R$^2$CS-NET integrates the robustness of online optimization with the efficiency and nonlinear capacity of deep learning methods. Signal correlation has been addressed through the network architecture. The adaptive sensing nature further makes it an ideal candidate for color image CS via leveraging channel correlation. Numerical experiments verify the proposed recurrent latent optimization design not only fulfills the adaptation motivation, but also outperforms classic long short-term memory (LSTM) architecture in the same scenario. The overall framework demonstrates hardware implementation feasibility, with leading robustness and generalization capability among existing deep CS benchmarks.