Detailed Feature Guided Generative Adversarial Pose Reconstruction Network

IEEE Access

Jinlin Hao¹  Xueyun Chen¹ 

[1] School of Electrical Engineering, Guangxi University, Nanning, China;

关键词: Face frontalization;    face pose reconstruction;    Generative Adversarial Network;    face rotation;   

DOI  :  10.1109/ACCESS.2021.3072277

来源: DOAJ

【 摘 要 】

Face frontalization is a critical and difficult task on face pose reconstruction. Previous researches use simple posture information as guidance, such as pose coding and facial landmarks. To explore the guidance effect of profile faces, we propose detailed features that provide much detailed information. In this paper, a Detailed Feature Guided Generative Adversarial Pose Reconstruction Network (DGPR) is proposed. Firstly, frontal pose coding and profile detailed features are fed into DGPR to generate detailed features of front face. Then, the second generator combines frontal detailed features and profile face to reconstruct front face. Besides, we propose a conditional enhancement loss to strengthen the guiding role of detailed features, and a smoothing loss to reduce edge sharpness in generated faces. Experimental results show that our method generates photorealistic front faces and outperforms state-of-the-art methods on M²FPA and CAS-PEAL. Specifically, DGPR improves the face recognition accuracy under pose angles of ±60°, ±75°, ±90° by 2%, 1%, and 6% respectively over the state-of-the-art methods on M²FPA, achieves the average rank-1 recognition rate to 99.95% and improves it by 0.05% on CAS-PEAL. These results demonstrate the effects of detailed features and corresponding modules.

【 授权许可】

Unknown