基于子块的三维网格模型检索

3D mesh model retrieval based on block

针对三维模型检索中如何准确计算模型间相似性问题,提出用子块局部相似性计算不同模型整体相似性的三维模型检索新方法.把经过线性细分和姿态调整的三维模型分割成不同的子块,构造每个子块的法向量直方图.采用从局部到整体的过程计算任意两个模型的相似度:根据直方图相交函数计算模型对应子块的局部相似性,结合子块点密度及局部相似性,采用改进的相似函数计算得到不同模型的整体相似度.和一些相似的检索算法比较,子块方法可以得到比较好的检索准确率.

To precisely compute the similarity between different models for content-based 3D retrieval, a 3D mesh model retrieval algorithm based on block similarity was proposed. In the preprocessing stage, an adaptive linear subdivision was performed to make the vertex distribution even over the given mesh, and pose estimation was undertaken to normalize the orientation of the model. The preprocessed model was segmented into a set of blocks, and the normal histogram was constructed for each block. The similarity calculation between 3D models was performed using a local-to-global strategy: The local similarity between blocks was computed, then an improved similarity function based on local block similarity and point density was defined to calculate the global similarity. Experimental results showed that the proposed algorithm could achieve better retrieving precision than other similar retrieving algorithms.