A New Deep Generative Network for Unsupervised Remote Sensing Single-Image Super-Resolution
View/ Open
Impact
Scholar |
Other documents of the author: Haut, Juan M.; Fernandez-Beltran, Ruben; Paoletti, Mercedes Eugenia; Plaza, Javier; Plaza, Antonio; Pla, Filiberto
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
A New Deep Generative Network for Unsupervised Remote Sensing Single-Image Super-ResolutionAuthor (s)
Date
2018-11Publisher
IEEEBibliographic citation
HAUT, Juan Mario, et al. A new deep generative network for unsupervised remote sensing single-image super-resolution. IEEE Transactions on Geoscience and Remote Sensing, 2018, 99: 1-19.Type
info:eu-repo/semantics/articlePublisher version
https://ieeexplore.ieee.org/abstract/document/8400496Version
info:eu-repo/semantics/submittedVersionAbstract
Super-resolution (SR) brings an excellent opportunity to improve a wide range of different remote sensing applications. SR techniques are concerned about increasing the image resolution while providing finer spatial ... [+]
Super-resolution (SR) brings an excellent opportunity to improve a wide range of different remote sensing applications. SR techniques are concerned about increasing the image resolution while providing finer spatial details than those captured by the original acquisition instrument. Therefore, SR techniques are particularly useful to cope with the increasing demand remote sensing imaging applications requiring fine spatial resolution. Even though different machine learning paradigms have been successfully applied in SR, more research is required to improve the SR process without the need of external high-resolution (HR) training examples. This paper proposes a new convolutional generator model to super-resolve low-resolution (LR) remote sensing data from an unsupervised perspective. That is, the proposed generative network is able to initially learn relationships between the LR and HR domains throughout several convolutional, downsampling, batch normalization, and activation layers. Then, the data are symmetrically projected to the target resolution while guaranteeing a reconstruction constraint over the LR input image. An experimental comparison is conducted using 12 different unsupervised SR methods over different test images. Our experiments reveal the potential of the proposed approach to improve the resolution of remote sensing imagery. [-]
Investigation project
Junta de Extremadura (GR15005) ; Generalitat Valenciana (APOSTD/2017/007) ; Spanish Ministry of Economy (project ESP2016-79503-C2-2-P)Rights
© 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/openAccess
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/openAccess
This item appears in the folowing collection(s)
- INIT_Articles [744]