TY - GEN
T1 - Multi-scale Generative Adversarial Learning for Facial Attribute Transfer
AU - Zhang, Yicheng
AU - Song, Li
AU - Xie, Rong
AU - Zhang, Wenjuan
N1 - Publisher Copyright:
© 2020, Springer Nature Singapore Pte Ltd.
PY - 2020
Y1 - 2020
N2 - Generative Adversarial Network (GAN) has shown its impressive ability on facial attribute transfer. One crucial part in facial attribute transfer is to retain the identity. To achieve this, most of existing approaches employ the L1 norm to maintain the cycle consistency, which tends to cause blurry results due to the weakness of the L1 loss function. To address this problem, we introduce the Structural Similarity Index (SSIM) in our GAN training objective as the measurement between input images and reconstructed images. Furthermore, we also incorporate a multi-scale feature fusion structure into the generator to facilitate feature learning and encourage long-term correlation. Qualitative and quantitative experiments show that our method has achieved better visual quality and fidelity than the baseline on facial attribute transfer.
AB - Generative Adversarial Network (GAN) has shown its impressive ability on facial attribute transfer. One crucial part in facial attribute transfer is to retain the identity. To achieve this, most of existing approaches employ the L1 norm to maintain the cycle consistency, which tends to cause blurry results due to the weakness of the L1 loss function. To address this problem, we introduce the Structural Similarity Index (SSIM) in our GAN training objective as the measurement between input images and reconstructed images. Furthermore, we also incorporate a multi-scale feature fusion structure into the generator to facilitate feature learning and encourage long-term correlation. Qualitative and quantitative experiments show that our method has achieved better visual quality and fidelity than the baseline on facial attribute transfer.
KW - Facial attribute transfer
KW - Generative Adversarial Network
KW - Multi-scale feature fusion
UR - http://www.scopus.com/inward/record.url?scp=85108458132&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-3341-9_8
DO - 10.1007/978-981-15-3341-9_8
M3 - Conference contribution
AN - SCOPUS:85108458132
SN - 9789811533402
T3 - Communications in Computer and Information Science
SP - 91
EP - 102
BT - Digital TV and Wireless Multimedia Communication - 16th International Forum, IFTC 2019, Revised Selected Papers
A2 - Zhai, Guangtao
A2 - Zhou, Jun
A2 - Yang, Hua
A2 - An, Ping
A2 - Yang, Xiaokang
PB - Springer Science and Business Media Deutschland GmbH
T2 - 16th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2019
Y2 - 19 September 2019 through 20 September 2019
ER -