Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport
This work addresses shape matching for computer graphics and vision, offering an incremental improvement over existing methods.
The paper tackles the problem of dense shape matching between deformed meshes by proposing a hierarchical learning design that integrates local patch-level and global shape-level information, achieving robust performance on public datasets without extensive training or refinement.
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.