A RESIDUAL DENSE GENERATIVE ADVERSARIAL NETWORK FOR PANSHARPENING WITH GEOMETRICAL CONSTRAINTS
hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
dc.contributor.author | GASTINEAU, Anaïs | |
hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
dc.contributor.author | AUJOL, Jean-François | |
hal.structure.identifier | Laboratoire de l'intégration, du matériau au système [IMS] | |
dc.contributor.author | BERTHOUMIEU, Yannick | |
hal.structure.identifier | Laboratoire de l'intégration, du matériau au système [IMS] | |
dc.contributor.author | GERMAIN, Christian | |
dc.date.accessioned | 2024-04-04T02:52:23Z | |
dc.date.available | 2024-04-04T02:52:23Z | |
dc.date.issued | 2020 | |
dc.date.conference | 2020-10-25 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/192062 | |
dc.description.abstractEn | The pansharpening problem consists in fusing a high resolution panchromatic image with a low resolution multispectral image in order to obtain a high resolution multispectral image. In this paper, we adapt a Residual Dense architecture for the generator in a Generative Adversarial Network framework. Indeed, this type of architecture avoids the vanishing gradient problem faced when training a network by re-injecting previous information thanks to dense and residual connections. Moreover, an important point for the pansharpening problem is to preserve the geometry of the image. Hence, we propose to add a regularization term in the loss function of the generator: it preserves the geometry of the target image so that a better solution is obtained. In addition, we propose geometrical measures that illustrate the advantages of this new method. | |
dc.description.sponsorship | Super-résolution d'images multi-échelles en sciences des matériaux avec des attributs géométriques - ANR-18-CE92-0050 | |
dc.language.iso | en | |
dc.subject.en | Pansharpening | |
dc.subject.en | Generative Adversarial Network | |
dc.subject.en | remote sensing | |
dc.subject.en | regularization | |
dc.subject.en | residual dense network | |
dc.title.en | A RESIDUAL DENSE GENERATIVE ADVERSARIAL NETWORK FOR PANSHARPENING WITH GEOMETRICAL CONSTRAINTS | |
dc.type | Communication dans un congrès | |
dc.subject.hal | Mathématiques [math] | |
bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
bordeaux.institution | Université de Bordeaux | |
bordeaux.institution | Bordeaux INP | |
bordeaux.institution | CNRS | |
bordeaux.conference.title | 27th IEEE international conference on image processing (ICIP 2020) | |
bordeaux.country | AE | |
bordeaux.conference.city | Abou Dabi | |
bordeaux.peerReviewed | oui | |
hal.identifier | hal-02859866 | |
hal.version | 1 | |
hal.invited | non | |
hal.proceedings | non | |
hal.popular | non | |
hal.audience | Internationale | |
hal.origin.link | https://hal.archives-ouvertes.fr//hal-02859866v1 | |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2020&rft.au=GASTINEAU,%20Ana%C3%AFs&AUJOL,%20Jean-Fran%C3%A7ois&BERTHOUMIEU,%20Yannick&GERMAIN,%20Christian&rft.genre=unknown |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |