TY - GEN
T1 - Deepcasd
T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
AU - Wen, Bihan
AU - Kamilov, Ulugbek S.
AU - Liu, Dehong
AU - Mansour, Hassan
AU - Boufounos, Petros T.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - Multi-spectral (MS) image super-resolution aims to reconstruct super-resolved multi-channel images from their low-resolution images by regularizing the image to be reconstructed. Recently data-driven regularization techniques based on sparse modeling and deep learning have achieved substantial improvements in single image reconstruction problems. Inspired by these data-driven methods, we develop a novel coupled analysis and synthesis dictionary (CASD) model for MS image super-resolution, by exploiting a regularizer that operates within, as well as across, multiple spectral channels using convolutional dictionaries. To learn the CASD model parameters, we propose a deep dictionary learning framework, named DeepCASD, by unfolding and training an end-to-end CASD based reconstruction network over an image data set. Experimental results show that the DeepCASD framework exhibits improved performance on multi-spectral image super-resolution compared to state-of-the-art learning based super-resolution algorithms.
AB - Multi-spectral (MS) image super-resolution aims to reconstruct super-resolved multi-channel images from their low-resolution images by regularizing the image to be reconstructed. Recently data-driven regularization techniques based on sparse modeling and deep learning have achieved substantial improvements in single image reconstruction problems. Inspired by these data-driven methods, we develop a novel coupled analysis and synthesis dictionary (CASD) model for MS image super-resolution, by exploiting a regularizer that operates within, as well as across, multiple spectral channels using convolutional dictionaries. To learn the CASD model parameters, we propose a deep dictionary learning framework, named DeepCASD, by unfolding and training an end-to-end CASD based reconstruction network over an image data set. Experimental results show that the DeepCASD framework exhibits improved performance on multi-spectral image super-resolution compared to state-of-the-art learning based super-resolution algorithms.
KW - Algorithm unfolding
KW - Convolutional dictionary
KW - Deep learning
KW - Multi-spectral imaging
KW - Super-resolution
UR - http://www.scopus.com/inward/record.url?scp=85054263427&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2018.8461795
DO - 10.1109/ICASSP.2018.8461795
M3 - Conference contribution
AN - SCOPUS:85054263427
SN - 9781538646588
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6503
EP - 6507
BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 15 April 2018 through 20 April 2018
ER -