A Dense Point-to-Point Alignment Method for Realistic 3D Face Morphing and Animation

摘要：

In this paper, we present a new closest point matching method to overcome the dense point-to-point alignment of scanned 3D faces. Instead of using the rigid spatial transformation in the traditional iterative closest point (ICP) algorithm,we adopt the thin plate spline (TPS) as the deformation between different 3D faces, because the TPS is a non-rigid transformation with good smooth property, and is suitable for formulating the complex variety of human facial morphology. To get one-to-one mapping, a closest point matching algorithm is proposed to find the correspondent point based on the common KD-tree method. Having constructed the dense correspondence between 3D faces, we create 3Dface morphing and animation by key-frames interpolation. The acceptable matching accuracy and the realistic 3D face morphing results demonstrate the capabilities of the point matching method.

关键词： Dense point matching thin plate spline (TPS) 3D face morphing 3D face animation

作者: Hu Yongli Zhou Mingquan Wu Zhongke

作者单位: College of Information Science and Technology Beijing Normal University Beijing 100875, China

会议类型: 国际会议

会议名称: 第四届计算机游戏开发技术研究国际会议(International Conference on Games Research and Development)

会议地点: 北京

会议语种:英文

页码: 91-96

在线出版日期: 2008-10-01（万方平台首次上网日期，不代表论文的发表时间）