Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Elastic Shape Analysis of Tree-like 3D Objects using Extended SRVF Representation
How can one analyze detailed 3D biological objects, such as neurons and botanical trees, that exhibit complex geometrical and topological variation? In this paper, we develop a novel mathematical framework for representi…
Bending the Future: Autoregressive Modeling of Temporal Knowledge Graphs in Curvature-Variable Hyperbolic Spaces
Recently there is an increasing scholarly interest in time-varying knowledge graphs, or temporal knowledge graphs (TKG). Previous research suggests diverse approaches to TKG reasoning that uses historical information. Ho…
Knowledge GraphsThe secret role of undesired physical effects in accurate shape sensing with eccentric FBGs
Fiber optic shape sensors have enabled unique advances in various navigation tasks, from medical tool tracking to industrial applications. Eccentric fiber Bragg gratings (FBG) are cheap and easy-to-fabricate shape sensor…
Deep LearningCompositional Hierarchical Representation of Shape Manifolds for Classification of Non-Manifold Shapes
We address the problem of statistical learning of shape models which are invariant to translation, rotation and scale in compositional hierarchies when data spaces of measurements and shape spaces are not topological man…
General ClassificationR2MF-Net: A Recurrent Residual Multi-Path Fusion Network for Robust Multi-directional Spine X-ray Segmentation
Accurate segmentation of spinal structures in X-ray images is a prerequisite for quantitative scoliosis assessment, including Cobb angle measurement, vertebral translation estimation and curvature classification. In rout…