TY - GEN
T1 - Facial expression synthesis by u-net conditional generative adversarial networks
AU - Wang, Xueping
AU - Li, Weixin
AU - Mu, Guodong
AU - Huang, Di
AU - Wang, Yunhong
N1 - Publisher Copyright:
© 2018 ACM.
PY - 2018/6/5
Y1 - 2018/6/5
N2 - High-level manipulation of facial expressions in images such as expression synthesis is challenging because facial expression changes are highly non-linear, and vary depending on the facial appearance. Identity of the person should also be well preserved in the synthesized face. In this paper, we propose a novel U-Net Conditioned Generative Adversarial Network (UC-GAN) for facial expression generation. U-Net helps retain the property of the input face, including the identity information and facial details. We also propose an identity preserving loss, which further improves the performance of our model. Both qualitative and quantitative experiments are conducted on the Oulu-CASIA and KDEF datasets, and the results show that our method can generate faces with natural and realistic expressions while preserve the identity information. Comparison with the state-of-the-art approaches also demonstrates the competency of our method.
AB - High-level manipulation of facial expressions in images such as expression synthesis is challenging because facial expression changes are highly non-linear, and vary depending on the facial appearance. Identity of the person should also be well preserved in the synthesized face. In this paper, we propose a novel U-Net Conditioned Generative Adversarial Network (UC-GAN) for facial expression generation. U-Net helps retain the property of the input face, including the identity information and facial details. We also propose an identity preserving loss, which further improves the performance of our model. Both qualitative and quantitative experiments are conducted on the Oulu-CASIA and KDEF datasets, and the results show that our method can generate faces with natural and realistic expressions while preserve the identity information. Comparison with the state-of-the-art approaches also demonstrates the competency of our method.
KW - Facial expression synthesis
KW - Generative adversarial network (gan)
KW - Identity preserving
UR - https://www.scopus.com/pages/publications/85053931284
U2 - 10.1145/3206025.3206068
DO - 10.1145/3206025.3206068
M3 - 会议稿件
AN - SCOPUS:85053931284
SN - 9781450350464
T3 - ICMR 2018 - Proceedings of the 2018 ACM International Conference on Multimedia Retrieval
SP - 283
EP - 290
BT - ICMR 2018 - Proceedings of the 2018 ACM International Conference on Multimedia Retrieval
PB - Association for Computing Machinery, Inc
T2 - 8th ACM International Conference on Multimedia Retrieval, ICMR 2018
Y2 - 11 June 2018 through 14 June 2018
ER -