A RESIDUAL DENSE GENERATIVE ADVERSARIAL NETWORK FOR PANSHARPENING WITH GEOMETRICAL CONSTRAINTS
Langue
en
Communication dans un congrès
Ce document a été publié dans
27th IEEE international conference on image processing (ICIP 2020), 2020-10-25, Abou Dabi. 2020
Résumé en anglais
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 ...Lire la suite >
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.< Réduire
Mots clés en anglais
Pansharpening
Generative Adversarial Network
remote sensing
regularization
residual dense network
Project ANR
Super-résolution d'images multi-échelles en sciences des matériaux avec des attributs géométriques - ANR-18-CE92-0050
Origine
Importé de halUnités de recherche