Symmetry-Aware Nonrigid Matching of Incomplete 3D Surfaces
Symmetry-Aware Nonrigid Matching of Incomplete 3D Surfaces
复制标题
DOI：
10.1109/cvpr.2014.534
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Y. Yoshiyasu;E. Yoshida;K. Yokoi;R. Sagawa
中科院分区：
文献类型：
--
作者：
Y. Yoshiyasu;E. Yoshida;K. Yokoi;R. Sagawa
我们提出了一个非刚性形状匹配技术建立对应的不完整的3D表面表现出内在的反射对称性。解决对称性模糊问题的关键是使用逐点局部网格描述符，该描述符具有方向并且因此对局部反射对称性敏感，例如区分左手和右手。我们设计了一种方法来计算描述符的方向，通过采取标量场的梯度称为平均扩散距离（ADD）。由于ADD是光滑定义在一个表面上，不变的等距/规模和强大的拓扑错误，非刚性变形的描述子的鲁棒性提高。此外，我们提出了一种称为迭代谱松弛的图匹配算法，它结合了谱嵌入和谱图匹配。这种提法允许我们定义成对约束的尺度不变的方式从k-最近邻本地对，使非等距变形可以鲁棒地处理。实验结果表明，我们的方法可以匹配具有全局内在对称性，数据不完整性和非等距变形的挑战性表面。
We present a nonrigid shape matching technique for establishing correspondences of incomplete 3D surfaces that exhibit intrinsic reflectional symmetry. The key for solving the symmetry ambiguity problem is to use a point-wise local mesh descriptor that has orientation and is thus sensitive to local reflectional symmetry, e.g. discriminating the left hand and the right hand. We devise a way to compute the descriptor orientation by taking the gradients of a scalar field called the average diffusion distance (ADD). Because ADD is smoothly defined on a surface, invariant under isometry/scale and robust to topological errors, the robustness of the descriptor to non-rigid deformations is improved. In addition, we propose a graph matching algorithm called iterative spectral relaxation which combines spectral embedding and spectral graph matching. This formulation allows us to define pairwise constraints in a scale-invariant manner from k-nearest neighbor local pairs such that non-isometric deformations can be robustly handled. Experimental results show that our method can match challenging surfaces with global intrinsic symmetry, data incompleteness and non-isometric deformations.