期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 24, 期 -, 页码 377-385出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2021.3050672
关键词
Faces; Lighting; Training; Generative adversarial networks; Image reconstruction; Gallium nitride; Face recognition; Deep learning; face; generative adversarial networks; neural networks
A novel architecture is proposed in this paper for manipulating facial expressions, head poses, and lighting conditions from a single monocular image. The method outperforms state-of-the-art methods in various scenarios and does not require target specific training.
We present a novel architecture for manipulating facial expressions, head poses, and lighting conditions from a single monocular image. Recent methods based on Generative Adversarial Networks show promising results in expression manipulation. However, the variation is either defined by a limited number of classes or not well suitable for explicit manipulation of different attributes such as pose and lighting conditions. Besides, state-of-the-art methods are mostly focused on frontal faces. Therefore, in this paper, a new Generative Adversarial Network architecture is proposed by explicitly conditioning on the appearance image space which is the product of direct manipulation of facial expressions, light and pose conditions of the face model in 3D space. In addition, the method only requires video sequences for training. Therefore, it is self-supervised. Unlike other face manipulation methods, the proposed method does not require target specific training. Large scale experiments show that our method outperforms state-of-the-art methods for different scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据