Generating Scenery Images with Larger Variety According to User Descriptions

In this paper, a framework based on generative adversarial networks is proposed to perform nature-scenery generation according to descriptions from the users. The desired place, time and seasons of the generated scenes can be specified with the help of text-to-image generation techniques. The framew...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hsu-Yung Cheng, Chih-Chang Yu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	text to image image generation generative adversarial networks Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/d4917a6f9c914dad8f72d117519c86a5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d4917a6f9c914dad8f72d117519c86a5
record_format	dspace
spelling	oai:doaj.org-article:d4917a6f9c914dad8f72d117519c86a52021-11-11T15:16:22ZGenerating Scenery Images with Larger Variety According to User Descriptions10.3390/app1121102242076-3417https://doaj.org/article/d4917a6f9c914dad8f72d117519c86a52021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10224https://doaj.org/toc/2076-3417In this paper, a framework based on generative adversarial networks is proposed to perform nature-scenery generation according to descriptions from the users. The desired place, time and seasons of the generated scenes can be specified with the help of text-to-image generation techniques. The framework improves and modifies the architecture of a generative adversarial network with attention models by adding the imagination models. The proposed attentional and imaginative generative network uses the hidden layer information to initialize the memory cell of the recurrent neural network to produce the desired photos. A data set containing different categories of scenery images is established to train the proposed system. The experiments validate that the proposed method is able to increase the quality and diversity of the generated images compared to the existing method. A possible application of road image generation for data augmentation is also demonstrated in the experimental results.Hsu-Yung ChengChih-Chang YuMDPI AGarticletext to imageimage generationgenerative adversarial networksTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10224, p 10224 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	text to image image generation generative adversarial networks Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	text to image image generation generative adversarial networks Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Hsu-Yung Cheng Chih-Chang Yu Generating Scenery Images with Larger Variety According to User Descriptions
description	In this paper, a framework based on generative adversarial networks is proposed to perform nature-scenery generation according to descriptions from the users. The desired place, time and seasons of the generated scenes can be specified with the help of text-to-image generation techniques. The framework improves and modifies the architecture of a generative adversarial network with attention models by adding the imagination models. The proposed attentional and imaginative generative network uses the hidden layer information to initialize the memory cell of the recurrent neural network to produce the desired photos. A data set containing different categories of scenery images is established to train the proposed system. The experiments validate that the proposed method is able to increase the quality and diversity of the generated images compared to the existing method. A possible application of road image generation for data augmentation is also demonstrated in the experimental results.
format	article
author	Hsu-Yung Cheng Chih-Chang Yu
author_facet	Hsu-Yung Cheng Chih-Chang Yu
author_sort	Hsu-Yung Cheng
title	Generating Scenery Images with Larger Variety According to User Descriptions
title_short	Generating Scenery Images with Larger Variety According to User Descriptions
title_full	Generating Scenery Images with Larger Variety According to User Descriptions
title_fullStr	Generating Scenery Images with Larger Variety According to User Descriptions
title_full_unstemmed	Generating Scenery Images with Larger Variety According to User Descriptions
title_sort	generating scenery images with larger variety according to user descriptions
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d4917a6f9c914dad8f72d117519c86a5
work_keys_str_mv	AT hsuyungcheng generatingsceneryimageswithlargervarietyaccordingtouserdescriptions AT chihchangyu generatingsceneryimageswithlargervarietyaccordingtouserdescriptions
_version_	1718435782739361792

Generating Scenery Images with Larger Variety According to User Descriptions

Ejemplares similares