Facial Image Generation by Generative Adversarial Networks using Weighted Conditions

Hiroki Adachi, Hiroshi Fukui, Takayoshi Yamashita, Hironobu Fujiyoshi

2019

Abstract

CGANs are generative models that depend on Deep Learning and can generate images that meet given conditions. However, if a network has a deep architecture, conditions do not provide enough information, so unnatural images are generated. In this paper, we propose a facial image generation method by introducing weighted conditions to CGANs. Weighted condition vectors are input in each layer of a generator, and then a discriminator is extend to multi-tasks so as to recognize input conditions. This approach can step-by-step reflect conditions inputted to the generator at every layer, fulfill the input conditions, and generate high quality images. We demonstrate the effectiveness of our method in both subjective and objective evaluation experiments.

Paper Citation

in Harvard Style

Adachi H., Fukui H., Yamashita T. and Fujiyoshi H. (2019). Facial Image Generation by Generative Adversarial Networks using Weighted Conditions. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 139-145. DOI: 10.5220/0007377601390145

in Bibtex Style

@conference{visapp19,
author={Hiroki Adachi and Hiroshi Fukui and Takayoshi Yamashita and Hironobu Fujiyoshi},
title={Facial Image Generation by Generative Adversarial Networks using Weighted Conditions},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={139-145},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007377601390145},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - Facial Image Generation by Generative Adversarial Networks using Weighted Conditions
SN - 978-989-758-354-4
AU - Adachi H.
AU - Fukui H.
AU - Yamashita T.
AU - Fujiyoshi H.
PY - 2019
SP - 139
EP - 145
DO - 10.5220/0007377601390145
PB - SciTePress