3D Bounding Box Generative Adversarial Nets

Ping Kuang, Haoshuang Wang

2019

Abstract

Recently, Generative Adversarial Networks (GANs) gradually applied to the generation of 3D objects and has achieved remarkable success, but at the same time, it also faces some problems, such as the training instability, low-quality samples and mode collapse. We propose a novel framework, namely 3D Bounding Box Generative Adversarial Network(3D-BBGAN), which can reduce the probability space of generation by adding conditional information. According this way, we can get 3D objects with more detailed geometries.

Paper Citation

in Harvard Style

Kuang P. and Wang H. (2019). 3D Bounding Box Generative Adversarial Nets.In Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC, ISBN 978-989-758-357-5, pages 117-121. DOI: 10.5220/0008096801170121

in Bibtex Style

@conference{ctisc19,
author={Ping Kuang and Haoshuang Wang},
title={3D Bounding Box Generative Adversarial Nets},
booktitle={Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC,},
year={2019},
pages={117-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008096801170121},
isbn={978-989-758-357-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC,
TI - 3D Bounding Box Generative Adversarial Nets
SN - 978-989-758-357-5
AU - Kuang P.
AU - Wang H.
PY - 2019
SP - 117
EP - 121
DO - 10.5220/0008096801170121