GSISTA-Net: generalized structure ISTA networks for image compressed sensing based on optimized unrolling algorithm

Image compressed sensing technology, particularly algorithm unrolling networks, has garnered significant attention in the field of compressed sensing due to their interpretability and high performance. However, similar to traditional compressed sensing methods, algorithm unrolling networks update and transmit pixel-level image data through specific instances of algorithms, often failing to fully exploit the rich information encoded in image features. This limitation results in information loss and incomplete feature fusion. In this paper, we introduce a novel approach: the Generalized Structure Iterative Shrinkage Threshold Algorithm (GSISTA), and present an algorithm extension network built upon GSISTA, referred to as GSISTA-Net. GSISTA-Net facilitates the efficient transfer of image feature information during the deep reconstruction stage through a jump connection structure. Additionally, it incorporates a dual-scale denoising module within the deep reconstruction stage to enhance denoising effectiveness. Our experimental results demonstrate that the proposed method surpasses the performance of five prominent state-of-the-art algorithms, specifically ReconNet, CSNet, ISTA-Net \(^+\) ${}^{+}$ , AMPNet, and OPINE-Net \(^+\) ${}^{+}$ , when evaluated in terms of both Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM).