Geometry Structure Preserving Based GAN for Multi-Pose Face Frontalization and Recognition

Geometry Structure Preserving Based GAN for Multi-Pose Face Frontalization and Recognition

Face frontalization is the process of converting a face image under arbitrary pose to an image with frontal pose. Benefited from significant improvement of generative adversarial networks (GAN), generative models can use face frontalization to overcome the problem of model degradation owing to the v...

Full description

Bibliographic Details
Main Authors: Xiao Luan, Hongmin Geng, Linghui Liu, Weisheng Li, Yuanyuan Zhao, Min Ren
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Face frontalization
pose
generative adversarial networks
self-attention
geometry structure preserving
Online Access:https://ieeexplore.ieee.org/document/9098952/

Internet

https://ieeexplore.ieee.org/document/9098952/

Similar Items