Non-rigid Shape Matching Using Geometry and Photometry
Non-rigid Shape Matching Using Geometry and Photometry
复制标题
使用几何和光度学的非刚性形状匹配
DOI：
10.1007/978-3-642-12297-2_62
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
R. Keriven
中科院分区：
文献类型：
--
作者：
N. Thorstensen;R. Keriven
在本文中，我们解决的问题，在不同的时间步长的可变形表面的三维重建之间的对应关系。我们假设（i）力学基础模型在表面上的点之间施加时间常数测地线距离;以及（ii）真实的表面的图像是可用的。例如，这是来自视频的时空形状（例如，多视图立体、视觉外壳等）的情况。当表面被假定为近似不可拉伸时。这些假设允许利用几何学和光度学。特别是，我们提出了一个能源为基础的制定的问题，扩展工作的Bronsteinet人。[1]的文件。一方面，我们表明，测光（i）在局部弹性变形或噪声表面的情况下提高了精度，（ii）当[1]由于模糊性（例如对称性）而失败时，仍然可以找到正确的解决方案。另一方面，使用几何体可以匹配经历过大运动的形状，这在通常的光度学方法中是不可能的。数值实验证明了我们的方法的有效性在合成和真实的数据。
In this paper, we tackle the problem of finding correspondences between three-dimensional reconstructions of a deformable surface at different time steps. We suppose that (i) the mechanical underlying model imposes time-constant geodesic distances between points on the surface; and that (ii) images of the real surface are available. This is for instance the case in spatio-temporal shape from videos (e.g. multi-view stereo, visual hulls, etc.) when the surface is supposed approximatively unstretchable. These assumptions allow to exploit both geometry and photometry. In particular we propose an energy based formulation of the problem, extending the work of Bronsteinet al.[1]. On the one hand, we show that photometry (i) improves accuracy in case of locally elastic deformations or noisy surfaces and (ii) allows to still find the right solution when [1] fails because of ambiguities (e.g. symmetries). On the other hand, using geometry makes it possible to match shapes that have undergone large motion, which is not possible with usual photometric methods. Numerical experiments prove the efficiency of our method on synthetic and real data.