Show simple item record

dc.contributor.authorAlvarez-Gila, Aitor
dc.contributor.authorVan de Weijer, Joost
dc.contributor.authorGarrote, Estibaliz
dc.date.accessioned2018-02-13T14:02:15Z
dc.date.available2018-02-13T14:02:15Z
dc.date.issued2017-10
dc.identifier.citationA. Alvarez-Gila, J. v d Weijer, and E. Garrote, “Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB,” in 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017, pp. 480–490.en
dc.identifier.urihttp://hdl.handle.net/11556/486
dc.description.abstractHyperspectral signal reconstruction aims at recovering the original spectral input that produced a certain trichromatic (RGB) response from a capturing device or observer. Given the heavily underconstrained, non-linear nature of the problem, traditional techniques leverage different statistical properties of the spectral signal in order to build informative priors from real world object reflectances for constructing such RGB to spectral signal mapping. However, most of them treat each sample independently, and thus do not benefit from the contextual information that the spatial dimensions can provide. We pose hyperspectral natural image reconstruction as an image to image mapping learning problem, and apply a conditional generative adversarial framework to help capture spatial semantics. This is the first time Convolutional Neural Networks -and, particularly, Generative Adversarial Networks- are used to solve this task. Quantitative evaluation shows a Root Mean Squared Error (RMSE) drop of 44.7% and a Relative RMSE drop of 47.0% on the ICVL natural hyperspectral image dataset.en
dc.language.isoengen
dc.publisherIEEEen
dc.titleAdversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGBen
dc.typeconferenceObjecten
dc.identifier.doi10.1109/ICCVW.2017.64en
dc.isiNoen
dc.rights.accessRightsopenAccessen
dc.subject.keywordsHyperspectral imagingen
dc.subject.keywordsDeep learningen
dc.subject.keywordsGenerative adversarial networksen
dc.subject.keywordsColoren
dc.page.final490en
dc.page.initial480en
dc.conference.title2017 IEEE International Conference on Computer Vision Workshops (ICCVW)en


Files in this item

Thumbnail

    Show simple item record