Light-Field Image Super-Resolution Using Convolutional Neural Network

Commercial light field cameras provide spatial and angular information, but their limited resolution becomes an important problem in practical use. In this letter, we present a novel method for light field image super-resolution (SR) to simultaneously up-sample both the spatial and angular resolutio...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2017-06, Vol.24 (6), p.848-852
Main Authors: Yoon, Youngjin, Jeon, Hae-Gon, Yoo, Donggeun, Lee, Joon-Young, Kweon, In So
Format: Article
Language:English
Subjects:
Cameras
Convolution
Convolutional neural network
light-field (LF) image
Neural networks
Signal resolution
Spatial resolution
super-resolution (SR)
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Commercial light field cameras provide spatial and angular information, but their limited resolution becomes an important problem in practical use. In this letter, we present a novel method for light field image super-resolution (SR) to simultaneously up-sample both the spatial and angular resolutions of a light field image via a deep convolutional neural network. We first augment the spatial resolution of each subaperture image by a spatial SR network, then novel views between super-resolved subaperture images are generated by three different angular SR networks according to the novel view locations. We improve both the efficiency of training and the quality of angular SR results by using weight sharing. In addition, we provide a new light field image dataset for training and validating the network. We train our whole network end-to-end, and show state-of-the-art performances on quantitative and qualitative evaluations.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2017.2669333