Expressive expression mapping with ratio images
Expressive expression mapping with ratio images
复制标题
DOI：
10.1145/383259.383289
复制
发表时间：
2001-08
期刊：
影响因子：
--
通讯作者：
Zicheng Liu;Ying Shan;Zhengyou Zhang
中科院分区：
文献类型：
--
作者：
Zicheng Liu;Ying Shan;Zhengyou Zhang
面部表情不仅表现出面部特征运动，而且表现出照明和外观的微妙变化（例如，面部皱纹和皱纹）。这些细节是重要的视觉线索，但它们很难合成。传统的表情映射技术考虑了特征的运动，而忽略了光照变化的细节。在本文中，我们提出了一种新的面部表情映射技术。我们捕捉一个人的表情在我们所谓的表情比率图像（ERI）的照明变化。结合几何变形，我们将ERI映射到任何其他人的面部图像，以生成更具表现力的面部表情。
Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance (e.g., facial creases and wrinkles). These details are important visual cues, but they are difficult to synthesize. Traditional expression mapping techniques consider feature motions while the details in illumination changes are ignored. In this paper, we present a novel technique for facial expression mapping. We capture the illumination change of one person's expression in what we call an expression ratio image (ERI). Together with geometric warping, we map an ERI to any other person's face image to generate more expressive facial expressions.