Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation

Generation of synthetic data is a challenging task. There are only a few significant works on RGB video generation and no pertinent works on RGB-D data generation. In the present work, we focus our attention on synthesizing RGB-D data which can further be used as dataset for various applications lik...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Richa Sharma, Manoj Sharma, Ankit Shukla, Santanu Chaudhury
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/a51be49e99d04078975762712f79cee2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a51be49e99d04078975762712f79cee2
record_format	dspace
spelling	oai:doaj.org-article:a51be49e99d04078975762712f79cee22021-11-22T01:10:59ZConditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation1563-514710.1155/2021/8358314https://doaj.org/article/a51be49e99d04078975762712f79cee22021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/8358314https://doaj.org/toc/1563-5147Generation of synthetic data is a challenging task. There are only a few significant works on RGB video generation and no pertinent works on RGB-D data generation. In the present work, we focus our attention on synthesizing RGB-D data which can further be used as dataset for various applications like object tracking, gesture recognition, and action recognition. This paper has put forward a proposal for a novel architecture that uses conditional deep 3D-convolutional generative adversarial networks to synthesize RGB-D data by exploiting 3D spatio-temporal convolutional framework. The proposed architecture can be used to generate virtually unlimited data. In this work, we have presented the architecture to generate RGB-D data conditioned on class labels. In the architecture, two parallel paths were used, one to generate RGB data and the second to synthesize depth map. The output from the two parallel paths is combined to generate RGB-D data. The proposed model is used for video generation at 30 fps (frames per second). The frame referred here is an RGB-D with the spatial resolution of 512 × 512.Richa SharmaManoj SharmaAnkit ShuklaSantanu ChaudhuryHindawi LimitedarticleEngineering (General). Civil engineering (General)TA1-2040MathematicsQA1-939ENMathematical Problems in Engineering, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939
spellingShingle	Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 Richa Sharma Manoj Sharma Ankit Shukla Santanu Chaudhury Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation
description	Generation of synthetic data is a challenging task. There are only a few significant works on RGB video generation and no pertinent works on RGB-D data generation. In the present work, we focus our attention on synthesizing RGB-D data which can further be used as dataset for various applications like object tracking, gesture recognition, and action recognition. This paper has put forward a proposal for a novel architecture that uses conditional deep 3D-convolutional generative adversarial networks to synthesize RGB-D data by exploiting 3D spatio-temporal convolutional framework. The proposed architecture can be used to generate virtually unlimited data. In this work, we have presented the architecture to generate RGB-D data conditioned on class labels. In the architecture, two parallel paths were used, one to generate RGB data and the second to synthesize depth map. The output from the two parallel paths is combined to generate RGB-D data. The proposed model is used for video generation at 30 fps (frames per second). The frame referred here is an RGB-D with the spatial resolution of 512 × 512.
format	article
author	Richa Sharma Manoj Sharma Ankit Shukla Santanu Chaudhury
author_facet	Richa Sharma Manoj Sharma Ankit Shukla Santanu Chaudhury
author_sort	Richa Sharma
title	Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation
title_short	Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation
title_full	Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation
title_fullStr	Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation
title_full_unstemmed	Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation
title_sort	conditional deep 3d-convolutional generative adversarial nets for rgb-d generation
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/a51be49e99d04078975762712f79cee2
work_keys_str_mv	AT richasharma conditionaldeep3dconvolutionalgenerativeadversarialnetsforrgbdgeneration AT manojsharma conditionaldeep3dconvolutionalgenerativeadversarialnetsforrgbdgeneration AT ankitshukla conditionaldeep3dconvolutionalgenerativeadversarialnetsforrgbdgeneration AT santanuchaudhury conditionaldeep3dconvolutionalgenerativeadversarialnetsforrgbdgeneration
_version_	1718418360539021312

Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation

Ejemplares similares