基于非均匀变形的人体模型定制算法

Personalizing human model by nonuniform deformation

提出了一种改进的人体模型定制算法,采用非均匀变形算法将照片中的人体外形特征添加到参考人体模型中,得到个性化和结构化的新模型.算法首先采集照片、合成参考图像、提取人体的轮廓线并将其划分成若干分段,然后在切割线空间构造从参考轮廓线(源于参考模型)中的一点到目标轮廓线(源于照片)中一点的二维映射,最后通过投影、二维映射和反投影改变参考模型中每个点的几何位置,从而生成新模型.实验结果表明,算法生成的结果不仅能够更加准确地体现出照片中人的外形特征,而且保证了结果模型的良好拼合,同时输入的照片不要求其中的人摆出规定的姿势.

An improved slice-space deforming algorithm for personalizing human model was presented, which adds shape details extracted from pictures to a reference model in order to get a personalized and structured model. The method begins with sample image collection and reference image generation followed by silhouette extraction and segmentation. Then it builds a mapping between pixels inside every pair of silhouette segments in the reference image and the sample image. This novel mapping algorithm is based on a slice-space representation that conforms to the natural features of human body. Finally, the position of every point in the reference model is changed through three steps, i.e. projection, two-dimensional mapping, and anti-projection. The deforming algorithm can extract the shape details from pictures more precisely and preserve the shape connectivity of the reference model in more situations. In addition, the proposed algorithm has not the special posture requirement for the person in input photos.