基于网格Laplace的三维几何模型分割

Segmentation of 3D Geometric Models Based on Mesh Laplace

模型分割是模型分析的重要方法和手段。针对已有网格分割算法对姿态敏感和计算速度慢的问题,提出了一种基于网格Laplace和k-means聚类的三维几何模型分割算法。通过网格Laplace将三维模型从空域嵌入到谱空间中进行分析,得到了模型的归一化形式,克服了姿态变化对分割结果的影响,并极大地减少了计算时间,获得了视觉上有意义的分割结果。实验结果表明,本算法能快速有效地实现网格模型的正确分割,并对模型姿态的变化有较好的鲁棒性。

Segmentation is one of important methods and means to analyze shapes. A novel algorithm for segmentation of 3D geometric models was proposed based on mesh Laplace and k-means cluster aiming at the problem that the existing mesh segmentation algorithms are sensitive to shape pose and time-consuming. Models are converted from spatial domain to spectral domain by using mesh Laplace in order to obtain the normalized forms, which are analyzed in spectral domain to avoid influence of variation of shape pose to segmentation results and greatly reduce the computing time. Experimental results show that the proposed algorithm is not only more efficient for generating correct and meaningful segmentations, but also more robust to variation of shape pose than existing algorithms.