TY - GEN
T1 - Stereo Super-Resolution via a Deep Convolutional Network
AU - Li, Junxuan
AU - You, Shaodi
AU - Robles-Kelly, Antonio
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/19
Y1 - 2017/12/19
N2 - In this paper, we present a method for stereo super-resolution which employs a deep network. The network is trained using the residual image so as to obtain a high resolution image from two, low resolution views. Our network is comprised by two deep sub-nets which share, at their output, a single convolutional layer. This last layer in the network delivers an estimate of the residual image which is then used, in combination with the left input frame of the stereo pair, to compute the super-resolved image at output. Each of these sub- networks is comprised by ten weight layers and, hence, allows our network to combine structural information in the image across image regions efficiently. Moreover, by learning the residual image, the network copes better with vanishing gradients and its devoid of gradient clipping operations. We illustrate the utility of our network for image-pair super-resolution and compare our network to its non-gradient trained analogue and alternatives elsewhere in the literature.
AB - In this paper, we present a method for stereo super-resolution which employs a deep network. The network is trained using the residual image so as to obtain a high resolution image from two, low resolution views. Our network is comprised by two deep sub-nets which share, at their output, a single convolutional layer. This last layer in the network delivers an estimate of the residual image which is then used, in combination with the left input frame of the stereo pair, to compute the super-resolved image at output. Each of these sub- networks is comprised by ten weight layers and, hence, allows our network to combine structural information in the image across image regions efficiently. Moreover, by learning the residual image, the network copes better with vanishing gradients and its devoid of gradient clipping operations. We illustrate the utility of our network for image-pair super-resolution and compare our network to its non-gradient trained analogue and alternatives elsewhere in the literature.
KW - Convolutional neural network
KW - Residual training
KW - Stereo super-resolution
UR - http://www.scopus.com/inward/record.url?scp=85048331631&partnerID=8YFLogxK
U2 - 10.1109/DICTA.2017.8227492
DO - 10.1109/DICTA.2017.8227492
M3 - Conference contribution
T3 - DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications
SP - 1
EP - 7
BT - DICTA 2017 - 2017 International Conference on Digital Image Computing
A2 - Guo, Yi
A2 - Murshed, Manzur
A2 - Wang, Zhiyong
A2 - Feng, David Dagan
A2 - Li, Hongdong
A2 - Cai, Weidong Tom
A2 - Gao, Junbin
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2017
Y2 - 29 November 2017 through 1 December 2017
ER -