SOURCE-LINKED INTELLIGENCE

TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

While data-driven 3D shape correspondence estimation has recently seen substantial progress, robust matching under partial observations and strong non-isometric deformations remains challenging. Existing learning-based approaches often rely on hand-crafted descriptors or template-based representations, whereas recent generative models over functional maps suffer from high inference cost, limited interpretability, and poor generalisation to partial shapes. In response to these limitations, this paper introduces TokenMatch, a new transformer-based unified model for estimating 3D shape correspond

Read original source ↗ Open in workspace

recordType

paper

region

Global