混合注意力机制的非刚性三维点云模型对应关系计算
Correspondence Calculation of Non-rigid 3D Point Shapes by Mixed Attention
-
摘要:针对非刚性三维点云模型对应关系构建中后处理过程计算复杂、算法泛化能力较差的问题, 提出一种采用混合注意力机制并以无监督学习的方式计算对应关系的算法. 首先引入点对特征改进边缘卷积, 使提取的特征蕴含点与点之间更多的相似位姿信息; 然后构建以余弦相似度计算为核心的混合注意力细化模块, 将模型间特征相似的部分编码为相似度矩阵; 最后, 直接利用相似度矩阵与坐标信息双向重建对应的模型, 获取最终的对应关系结果. 在 SURREAL, SHREC’19, SMAL 和 TOSCA 数据集上的定性和定量实验结果表明, 所提算法与 CorrNet3D 算法相比, 在利用原始模型与重建模型之间的欧氏距离衡量对应关系误差时平均误差在 SHREC’19, TOSCA 数据集上分别减少了 0.19 与 5.0, 在不同误差容忍度下对应关系准确率分别提高了 9.26%, 20.41%, 且在不同数据集上具有良好的泛化能力.Abstract: Aiming at the complicated post-processing and poor generalization ability of correspondence calculation of non-rigid 3D point cloud shapes, a method that employs a mixed attention mechanism and unsupervised learning to calculate correspondence is proposed in this paper. First, the point pair feature improves the EdgeConv so that the extracted features can contain more similar pose information between points. Then, a mixed attention similarity refinement module is constructed by calculating cosine similarity, and the similar parts of features between models encode as a similarity matrix. Finally, the corresponding model is directly reconstructed in both directions using the similarity matrix and the coordinate information to compute the final correspondence. The qualitative and quantitative experimental results on SURREAL, SHREC’19, SMAL, and TOSCA datasets show that the proposed algorithm outperforms the CorrNet3D algorithm. Specifically, the average error in measuring correspondence error using the Euclidean distance between the original and reconstructed shapes is reduced by 0.19 and 5.0 on the SHREC’19 and TOSCA datasets, respectively. The correspondence accuracy is also improved by 9.26% and 20.41% when the tolerance error is 10%. Furthermore, the proposed algorithm exhibits good generalization ability across different datasets.