ALVAREZ-GILA, AITOR; WEIJER, JOOST VAN DE; GARROTE, ESTÍBALIZ Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB (Artículo en actas) 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 480–490, 2017, (The arxiv.org version contains updated results.). @inproceedings{alvarez-gila_adversarial_2017, title = {Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB}, author = {AITOR ALVAREZ-GILA and JOOST VAN DE WEIJER and ESTÍBALIZ GARROTE}, url = {https://arxiv.org/abs/1709.00265}, doi = {10.1109/ICCVW.2017.64}, year = {2017}, date = {2017-01-01}, booktitle = {2017 IEEE International Conference on Computer Vision Workshops (ICCVW)}, pages = {480--490}, abstract = {Hyperspectral 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.}, note = {The arxiv.org version contains updated results.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Hyperspectral 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. |

## 2017 |

ALVAREZ-GILA, AITOR; WEIJER, JOOST VAN DE; GARROTE, ESTÍBALIZ Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB (Artículo en actas) 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 480–490, 2017, (The arxiv.org version contains updated results.). (Resumen | Enlaces | BibTeX | Etiquetas: cnn, color, GAN, hyperspectral, neural networks) @inproceedings{alvarez-gila_adversarial_2017, title = {Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB}, author = {AITOR ALVAREZ-GILA and JOOST VAN DE WEIJER and ESTÍBALIZ GARROTE}, url = {https://arxiv.org/abs/1709.00265}, doi = {10.1109/ICCVW.2017.64}, year = {2017}, date = {2017-01-01}, booktitle = {2017 IEEE International Conference on Computer Vision Workshops (ICCVW)}, pages = {480--490}, abstract = {Hyperspectral 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.}, note = {The arxiv.org version contains updated results.}, keywords = {cnn, color, GAN, hyperspectral, neural networks}, pubstate = {published}, tppubtype = {inproceedings} } Hyperspectral 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. |