File(s) under permanent embargo
Stereo super-resolution via a deep convolutional network
conference contribution
posted on 2017-01-01, 00:00 authored by Junxuan Li, Shaodi You, Antonio Robles-KellyAntonio Robles-KellyIn 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.
History
Event
Australian Pattern Recognition Society. Conference (2017 : Sydney, N.S.W.)Series
Australian Pattern Recognition Society ConferencePagination
858 - 864Publisher
Institute of Electrical and Electronics EngineersLocation
Sydney, N.S.W.Place of publication
Piscataway, N.J.Publisher DOI
Start date
2017-11-29End date
2017-12-01ISBN-13
978-1-5386-2839-3Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2017, IEEEEditor/Contributor(s)
[Unknown]Title of proceedings
DICTA 2017 : Proceedings of the 2017 International Conference on Digital Image Computing: Techniques and ApplicationsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC