A RESIDUAL DENSE GENERATIVE ADVERSARIAL NETWORK FOR PANSHARPENING WITH GEOMETRICAL CONSTRAINTS - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

A RESIDUAL DENSE GENERATIVE ADVERSARIAL NETWORK FOR PANSHARPENING WITH GEOMETRICAL CONSTRAINTS

Résumé

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.
Fichier principal
Vignette du fichier
pre_print_icip2020.pdf (473.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02859866 , version 1 (08-06-2020)

Identifiants

  • HAL Id : hal-02859866 , version 1

Citer

Anaïs Gastineau, Jean-François Aujol, Yannick Berthoumieu, Christian Germain. A RESIDUAL DENSE GENERATIVE ADVERSARIAL NETWORK FOR PANSHARPENING WITH GEOMETRICAL CONSTRAINTS. 27th IEEE international conference on image processing (ICIP 2020), Oct 2020, Abou Dabi, United Arab Emirates. ⟨hal-02859866⟩
89 Consultations
346 Téléchargements

Partager

Gmail Facebook X LinkedIn More