当前位置: X-MOL 学术Comput. Animat. Virtual Worlds › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Facial expression animation through action units transfer in latent space
Computer Animation and Virtual Worlds ( IF 1.1 ) Pub Date : 2020-07-01 , DOI: 10.1002/cav.1946
Yachun Fan 1 , Feng Tian 2 , Xiaohui Tan 3 , Housen Cheng 1
Affiliation  

Automatic animation synthesis has attracted much attention from the community. As most existing methods take a small number of discrete expressions rather than continuous expressions, their integrity and reality of the facial expressions is often compromised. In addition, the easy manipulation with simple inputs and unsupervised processing, although being important to the automatic facial expression animation applications, is relatively less concerned. To address these issues, we propose an unsupervised continuous automatic facial expression animation approach through action units (AU) transfer in the latent space of generative adversarial networks. The expression descriptor which is depicted with AU vector is transferred into the input image without the need of labeled pairs of images and even without their expressions and further network training. We also propose a new approach to quickly generate input image's latent code and cluster the boundaries of different AU attributes with their latent codes. Two latent code operators, vector addition and continuous interpolation, are leveraged for facial expression animation simulating align with the boundaries in the latent space. Experiments have shown that the proposed approach is effective on facial expression translation and animation synthesis.

中文翻译:

通过动作单元在潜在空间中转移的面部表情动画

自动动画合成引起了社区的广泛关注。由于大多数现有方法采用少量离散表情而不是连续表情,因此它们的面部表情的完整性和真实性经常受到损害。此外,简单的输入和无监督处理的简单操作虽然对自动面部表情动画应用很重要,但相对较少受到关注。为了解决这些问题,我们提出了一种无监督的连续自动面部表情动画方法,通过生成对抗网络的潜在空间中的动作单元(AU)转移。用 AU 向量描述的表达描述符被传输到输入图像中,不需要标记的图像对,甚至不需要它们的表达和进一步的网络训练。我们还提出了一种新方法来快速生成输入图像的潜在代码,并将不同 AU 属性的边界与其潜在代码进行聚类。两个潜在代码运算符,向量加法和连续插值,用于面部表情动画模拟与潜在空间中的边界对齐。实验表明,所提出的方法在面部表情翻译和动画合成方面是有效的。矢量加法和连续插值,用于面部表情动画模拟与潜在空间中的边界对齐。实验表明,所提出的方法在面部表情翻译和动画合成方面是有效的。矢量加法和连续插值,用于面部表情动画模拟与潜在空间中的边界对齐。实验表明,所提出的方法在面部表情翻译和动画合成方面是有效的。
更新日期:2020-07-01
down
wechat
bug