2D vs. 3D deformable face models: Representational power, construction, and real-time fitting
2D vs. 3D deformable face models: Representational power, construction, and real-time fitting
复制标题
DOI：
10.1007/s11263-007-0043-2
复制
发表时间：
2007-10-01
影响因子：
19.5
通讯作者：
Baker, Simon
中科院分区：
文献类型：
--
作者：
Matthews, Iain;Xiao, Jing;Baker, Simon
基于模型的人脸分析是一种通用范例，其应用包括人脸识别、表情识别、唇读、头部姿势估计和凝视估计。人脸模型首先从训练数据集合中构建，可以是2D图像，也可以是3D距离扫描。然后将人脸模型拟合到输入图像和应用程序中使用的模型参数中。大多数现有的面部模型可以分为2D（如活动外观模型）或3D（如变形模型）。在本文中，我们沿着三个轴比较了二维和三维人脸模型：(1)表征能力，(2)构造和(3)实时拟合。对于每个轴，我们依次概述了使用2D或3D面部模型所产生的差异。
Model-based face analysis is a general paradigm with applications that include face recognition, expression recognition, lip-reading, head pose estimation, and gaze estimation. A face model is first constructed from a collection of training data, either 2D images or 3D range scans. The face model is then fit to the input image(s) and the model parameters used in whatever the application is. Most existing face models can be classified as either 2D (e.g. Active Appearance Models) or 3D (e.g. Morphable Models). In this paper we compare 2D and 3D face models along three axes: (1) representational power, (2) construction, and (3) real-time fitting. For each axis in turn, we outline the differences that result from using a 2D or a 3D face model.