ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing

By Yan Yang, Jian Sun, Huibin Li, Zongben Xu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

829 citations recorded by the source corpus.

Compressive sensing (CS) is an effective technique for reconstructing image from a small amount of sampled data. It has been widely applied in medical imaging, remote sensing, image compression, etc. In this paper, we propose two versions of a novel deep learning architecture, dubbed as ADMM-CSNet, by combining the traditional model-based CS method and data-driven deep learning method for image reconstruction from sparsely sampled measurements. We first consider a generalized CS model for image reconstruction with undetermined regularizations in undetermined transform domains, and then two efficient solvers using Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing the model are proposed. We further unroll and generalize the ADMM algorithm to be two deep architectures, in which all parameters of the CS model and the ADMM algorithm are discriminatively learned by end-to-end training. For both applications of fast CS complex-valued MR imaging and CS imaging of real-valued natural images, the proposed ADMM-CSNet achieved favorable reconstruction accuracy in fast computational speed compared with the traditional and the other deep learning methods.

Subfields: Biomedical Engineering, Computational Mechanics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/68ff94fd4c6c93b2da78adcda53ff49ded9f8b2a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computational Mechanics

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing (2019, methodology): “However, for better performance, the method in [14] learns both of them from an unrolled network.”
Deep Magnetic Resonance Image Reconstruction: Inverse Problems Meet Neural Networks (2020, neutral): “Deep-learning-based MRI reconstruction methods can be approximately categorized as unrolling-based approaches [5]–[12] and those not based on unrolling [13]–[28].”
FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging (2020, methodology): “(1) from a low-dimension data b to a high dimensional image x [19].”
Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data (2019, background): “istically combined with multi-coil acquisitions (10-12). At high acceleration rates, parallel imaging suffers from noise amplification (13-15), while compressed sensing may lead to residual artifacts (16,17). Furthermore, compressed sensing reconstruction is computationally lengthy in nature and typ”