TY - GEN
T1 - Deep learning based image super-resolution with coupled backpropagation
AU - Guo, Tiantong
AU - Mousavi, Hojjat S.
AU - Monga, Vishal
N1 - Funding Information:
Research was supported by National Science Foundation CAREER Award.
Publisher Copyright:
© 2016 IEEE.
PY - 2017/4/19
Y1 - 2017/4/19
N2 - Recently deep learning methods have been applied to image super-resolution (SR). Typically, these approaches involve training a single convolutional neural network that is trained to perform resolution enhancement. We propose a new low-complexity but effective algorithm called Superresolution with Coupled Backpropagation (SR-CBP) which builds two Coupled Auto-encoder Networks (CAN), resp. the high-resolution (HR) and low-resolution (LR) networks, that capture the features of both high and low resolution images. The two networks in CAN have the ability to self-reconstruct its own input. Specifically, SR-CBP allows joint training of the LR and HR networks to have middle layer representations that agree for a pair of images (high-resolution image and its corresponding low-resolution version). For an LR input image, its middle layer representation obtained via the trained LR network can be fed into the HR network to generate the SR result. Preliminary experiments show that SR-CBP can produce better results than state of the art single image superresolution methods based on sparse representations. The memory and storage requirements of CAN are lesser than existing deep learning based SR methods.
AB - Recently deep learning methods have been applied to image super-resolution (SR). Typically, these approaches involve training a single convolutional neural network that is trained to perform resolution enhancement. We propose a new low-complexity but effective algorithm called Superresolution with Coupled Backpropagation (SR-CBP) which builds two Coupled Auto-encoder Networks (CAN), resp. the high-resolution (HR) and low-resolution (LR) networks, that capture the features of both high and low resolution images. The two networks in CAN have the ability to self-reconstruct its own input. Specifically, SR-CBP allows joint training of the LR and HR networks to have middle layer representations that agree for a pair of images (high-resolution image and its corresponding low-resolution version). For an LR input image, its middle layer representation obtained via the trained LR network can be fed into the HR network to generate the SR result. Preliminary experiments show that SR-CBP can produce better results than state of the art single image superresolution methods based on sparse representations. The memory and storage requirements of CAN are lesser than existing deep learning based SR methods.
UR - http://www.scopus.com/inward/record.url?scp=85019245288&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019245288&partnerID=8YFLogxK
U2 - 10.1109/GlobalSIP.2016.7905839
DO - 10.1109/GlobalSIP.2016.7905839
M3 - Conference contribution
AN - SCOPUS:85019245288
T3 - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings
SP - 237
EP - 241
BT - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016
Y2 - 7 December 2016 through 9 December 2016
ER -