论文标题
弯曲图：使用门控的最佳传输的分层形状匹配
Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport
论文作者
论文摘要
对于计算机图形和视觉社区来说，形状匹配一直是一个长期研究的问题。目的是预测具有一定程度变形的网格之间的密集对应关系。现有方法要么考虑采样点的局部描述，要么根据全局形状信息发现对应关系。在这项工作中，我们研究了分层学习设计，并将其结合到本地贴片级信息和全球形状级别的结构。这种灵活的表示可以实现对应的预测，并为匹配阶段提供了丰富的功能。最后，我们通过在非征信节点上经常更新特征来了解形状之间的全球一致对应关系，从而提出了一种新颖的最佳传输求解器。我们对公开数据集的结果表明，在存在严重变形的情况下，不需要进行广泛的培训或完善的情况下表现出色。
Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the local description of sampled points or discover correspondences based on global shape information. In this work, we investigate a hierarchical learning design, to which we incorporate local patch-level information and global shape-level structures. This flexible representation enables correspondence prediction and provides rich features for the matching stage. Finally, we propose a novel optimal transport solver by recurrently updating features on non-confident nodes to learn globally consistent correspondences between the shapes. Our results on publicly available datasets suggest robust performance in presence of severe deformations without the need for extensive training or refinement.
