TY - JOUR
T1 - Deep-Learning Supervised Snapshot Compressive Imaging Enabled by an End-to-End Adaptive Neural Network
AU - Marquez, Miguel
AU - Lai, Yingming
AU - Liu, Xianglei
AU - Jiang, Cheng
AU - Zhang, Shian
AU - Arguello, Henry
AU - Liang, Jinyang
N1 - Publisher Copyright:
© 2007-2012 IEEE.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Snapshot compressive imaging (SCI) is an advanced approach for single-shot high-dimensional data visualization. Deep learning is popularly used to improve SCI's performance. However, most existing methods are merely used as a replacement for analytical-modeling-based image reconstruction. Moreover, these models cling to the conventional random coded apertures and often presume a linear shearing operation. To overcome these limitations, we develop a new end-to-end convolutional neural network, termed deep high-dimensional adaptive net (D-HAN) that offers multi-faceted supervision to SCI by optimizing the coded aperture, sensing the shearing operation, and reconstructing three-dimensional datacubes. The D-HAN is implemented in two representative SCI systems for ultrahigh-speed imaging and hyperspectral imaging. The D-HAN is envisioned to benefit SCI in system design, image reconstruction, and performance evaluation.
AB - Snapshot compressive imaging (SCI) is an advanced approach for single-shot high-dimensional data visualization. Deep learning is popularly used to improve SCI's performance. However, most existing methods are merely used as a replacement for analytical-modeling-based image reconstruction. Moreover, these models cling to the conventional random coded apertures and often presume a linear shearing operation. To overcome these limitations, we develop a new end-to-end convolutional neural network, termed deep high-dimensional adaptive net (D-HAN) that offers multi-faceted supervision to SCI by optimizing the coded aperture, sensing the shearing operation, and reconstructing three-dimensional datacubes. The D-HAN is implemented in two representative SCI systems for ultrahigh-speed imaging and hyperspectral imaging. The D-HAN is envisioned to benefit SCI in system design, image reconstruction, and performance evaluation.
KW - Snapshot compressive imaging
KW - coded aperture design
KW - end-to-end neural networks
KW - high-dimensional imaging
KW - shearing estimation
UR - https://www.scopus.com/pages/publications/85132522291
U2 - 10.1109/JSTSP.2022.3172592
DO - 10.1109/JSTSP.2022.3172592
M3 - 文章
AN - SCOPUS:85132522291
SN - 1932-4553
VL - 16
SP - 688
EP - 699
JO - IEEE Journal on Selected Topics in Signal Processing
JF - IEEE Journal on Selected Topics in Signal Processing
IS - 4
ER -