Text-to-image synthesis is a research topic that has not yet been addressed by the remote sensing community. It consists in learning a mapping from text description to image pixels. In this paper, we propose to address this topic for the very first time. More specifically, our objective is to convert ancient text descriptions of geographic areas written by past explorers into an equivalent remote sensing image. To this effect, we rely on generative adversarial networks (GANs) to learn the mapping. GANs aim to represent the distribution of a dataset using weights of a deep neural network, which are trained as an adversarial competition between two networks. We collected ancient texts dating back to 7 BC to train our network and obtained interesting results, which form the basis to highlight future research directions to advance this new topic.
Towards Generating Remote Sensing Images of the Far Past / Bejiga, M. B.; Melgani, F.. - (2019), pp. 9502-9505. (Intervento presentato al convegno 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 tenutosi a Yokohama, Japan, Convention Center "Pacifico Yokohama" nel 2019) [10.1109/IGARSS.2019.8899834].
Towards Generating Remote Sensing Images of the Far Past
Bejiga M. B.;Melgani F.
2019-01-01
Abstract
Text-to-image synthesis is a research topic that has not yet been addressed by the remote sensing community. It consists in learning a mapping from text description to image pixels. In this paper, we propose to address this topic for the very first time. More specifically, our objective is to convert ancient text descriptions of geographic areas written by past explorers into an equivalent remote sensing image. To this effect, we rely on generative adversarial networks (GANs) to learn the mapping. GANs aim to represent the distribution of a dataset using weights of a deep neural network, which are trained as an adversarial competition between two networks. We collected ancient texts dating back to 7 BC to train our network and obtained interesting results, which form the basis to highlight future research directions to advance this new topic.File | Dimensione | Formato | |
---|---|---|---|
Paper.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
921.29 kB
Formato
Adobe PDF
|
921.29 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione