Robust Deep Compressive Sensing with Recurrent-Residual Structural Constraints
This work addresses the challenge of efficient and robust image compressive sensing for applications like medical imaging or video processing, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the problem of deep compressive sensing by introducing R^2CS-NET, a framework that combines adaptive online optimization with deep learning for efficient image reconstruction, achieving leading robustness and generalization in benchmarks.
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.