Group-Valued Regularization Framework for Motion Segmentation of Dynamic Non-rigid Shapes
Group-Valued Regularization Framework for Motion Segmentation of Dynamic Non-rigid Shapes
复制标题
用于动态非刚性形状运动分割的群值正则化框架
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
R. Kimmel
中科院分区：
文献类型：
--
作者：
G. Rosman;M. Bronstein;A. Bronstein;A. Wolf;R. Kimmel
对关节运动的理解在机械工程、电影工业、图形学和视觉领域的许多应用中起着重要的作用。在本文中，我们研究了基于运动的分割关节的3D形状到刚性部件。我们提出的问题，找到一个组值映射之间的形状描述的运动，迫使它有利于分段刚性运动。我们的计算遵循Mumford-Shah分割的Ambrosio-Tortorelli方案的精神，具有适合运动模型的组性质的扩散分量。实验结果证明了该方法在非刚体运动分割中的有效性。
Understanding of articulated shape motion plays an important role in many applications in the mechanical engineering, movie industry, graphics, and vision communities. In this paper, we study motion-based segmentation of articulated 3D shapes into rigid parts. We pose the problem as finding a group-valued map between the shapes describing the motion, forcing it to favor piecewise rigid motions. Our computation follows the spirit of the Ambrosio-Tortorelli scheme for Mumford-Shah segmentation, with a diffusion component suited for the group nature of the motion model. Experimental results demonstrate the effectiveness of the proposed method in non-rigid motion segmentation.