基于形状匹配变形模型的三维人脸重构

3D Reconstruction of Human Face Based on Shape Match Morphing Model

为了从多幅人脸图像构造三维人脸结构,通常需要自动提取不同图像中的对应特征点,这往往是很难完成的.为了避免这个困难,本文建立了一个基于形状匹配的三维变形模型,在保证形状最佳匹配的条件下,实现对人脸图像姿态的估计和三维人脸重构.模型采用径向基函数对通用头部模型进行变形,用形状上下文来描述点之间的形状相似性,形状距离用来描述头部模型和人脸图像整体形状上的相似性,从而实现形状最佳匹配意义上的三维重构.实验表明,本文的算法只需要在人脸图像中提取特征点集,不需进行配准,就可以恢复出令人满意的三维头部结构.

Automatic extraction and matching of a set of significant feature points on different image views on the face is a very hard machine task.In this paper,in order to bypass this problem,our method recovers both the pose and the 3-D face coordinates using shape match morphing model and iteratJve minimization of a metric based on the structure match. A radial basis function （RBF） in 3D is used to morph a generic face into the specific face structure and shape context （SC） is used to descript point shape. Based on RBF and SC, shape distance is used to metric the similarity of two shapes. Experiment results are shown for images of real faces and promising result are obtained.