TY - JOUR
T1 - NL-CS Net
T2 - Deep Learning with Non-local Prior for Image Compressive Sensing
AU - Bian, Shuai
AU - Qi, Shouliang
AU - Li, Chen
AU - Yao, Yudong
AU - Teng, Yueyang
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
PY - 2024/8
Y1 - 2024/8
N2 - Deep learning has been applied to compressive sensing (CS) of images successfully in recent years. However, existing network-based methods are often trained as the black box, in which the lack of prior knowledge is often the bottleneck for further performance improvement. To overcome this drawback, this paper proposes a novel CS method using non-local prior which combines the interpretability of the traditional optimization methods with the speed of network-based methods, called NL-CS Net. We unroll each phase from iteration of the augmented Lagrangian method solving non-local and sparse regularized optimization problem by a network. NL-CS Net is composed of the up-sampling module and the recovery module. In the up-sampling module, we use learnable up-sampling matrix instead of a predefined one. In the recovery module, patch-wise non-local network is employed to capture long-range feature correspondences. Important parameters involved (e.g. sampling matrix, nonlinear transforms, shrinkage thresholds, step size, etc.) are learned end-to-end, rather than hand-crafted. Furthermore, to facilitate practical implementation, orthogonal and binary constraints on the sampling matrix are simultaneously adopted. Extensive experiments on natural images and magnetic resonance imaging demonstrate that the proposed method outperforms the state-of-the-art methods while maintaining great interpretability and speed.
AB - Deep learning has been applied to compressive sensing (CS) of images successfully in recent years. However, existing network-based methods are often trained as the black box, in which the lack of prior knowledge is often the bottleneck for further performance improvement. To overcome this drawback, this paper proposes a novel CS method using non-local prior which combines the interpretability of the traditional optimization methods with the speed of network-based methods, called NL-CS Net. We unroll each phase from iteration of the augmented Lagrangian method solving non-local and sparse regularized optimization problem by a network. NL-CS Net is composed of the up-sampling module and the recovery module. In the up-sampling module, we use learnable up-sampling matrix instead of a predefined one. In the recovery module, patch-wise non-local network is employed to capture long-range feature correspondences. Important parameters involved (e.g. sampling matrix, nonlinear transforms, shrinkage thresholds, step size, etc.) are learned end-to-end, rather than hand-crafted. Furthermore, to facilitate practical implementation, orthogonal and binary constraints on the sampling matrix are simultaneously adopted. Extensive experiments on natural images and magnetic resonance imaging demonstrate that the proposed method outperforms the state-of-the-art methods while maintaining great interpretability and speed.
KW - Compressive sensing
KW - Image reconstruction
KW - Neural network
KW - Non-local prior
UR - http://www.scopus.com/inward/record.url?scp=85192535773&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192535773&partnerID=8YFLogxK
U2 - 10.1007/s00034-024-02699-x
DO - 10.1007/s00034-024-02699-x
M3 - Article
AN - SCOPUS:85192535773
SN - 0278-081X
VL - 43
SP - 5191
EP - 5210
JO - Circuits, Systems, and Signal Processing
JF - Circuits, Systems, and Signal Processing
IS - 8
ER -