Metraipolis › archive › dc_d2b165cafcb4

TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation — arXiv:2609.04202

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04202
License (as archived)
CC0-1.0
Archived
2026-10-17T02:56:37.832Z
SHA-256 of the archived text
ee8bad21cea73b2640aac22bd0ce681dee012625c4c7ca3470cb6a50ea01600e
Stable URL of this page
https://metraipolis.com/documento/dc_d2b165cafcb4

How to cite

TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation — arXiv:2609.04202 — arXiv (en), https://arxiv.org/abs/2609.04202 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2b165cafcb4 (Metraipolis archive dc_d2b165cafcb4, sha256 ee8bad21cea73b2640aac22bd0ce681dee012625c4c7ca3470cb6a50ea01600e)
BibTeX
@misc{dcd2b165cafcb4,
  title = {TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation — arXiv:2609.04202},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04202},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2b165cafcb4; sha256 ee8bad21cea73b2640aac22bd0ce681dee012625c4c7ca3470cb6a50ea01600e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04202. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 correspondences. Our feed-forward approach trained exclusively on BeCoS, a challenging non-isometric partial-to-partial shape-matching dataset, can generalise to matching full shapes without retraining or fine-tuning. TokenMatch uses self- and cross-attention mechanisms to efficiently learn patch-level and point-level relations as well as dense correspondences between shape pairs. Our core insight is that meshes can be adaptively tokenised into patches using shape curvature guidance, enabling effective learning of shape-specific geometric descriptors for correspondence estimation. We evaluate TokenMatch on standard benchmarks for partial and full shape matching, including CP2P, PSMAL, BeCoS, FAUST, SCAPE, and SHREC'19. Our method achieves consistently high performance, in most cases outperforming existing methods for partial and full shape matching in the mean geodesic error and intersection-over-union metrics, while also running faster at sub-second inference speeds.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04202 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T02:27:19.020Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).