Metraipolis › archive › dc_011079da189c

Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformation — arXiv:2609.37071

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37071
License (as archived)
CC0-1.0
Archived
2026-10-07T18:40:53.563Z
SHA-256 of the archived text
400707a335287f476f65ec274296359511579c18c0af1552e72aa5b7df0b3859
Stable URL of this page
https://metraipolis.com/documento/dc_011079da189c

How to cite

Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformation — arXiv:2609.37071 — arXiv (en), https://arxiv.org/abs/2609.37071 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_011079da189c (Metraipolis archive dc_011079da189c, sha256 400707a335287f476f65ec274296359511579c18c0af1552e72aa5b7df0b3859)
BibTeX
@misc{dc011079da189c,
  title = {Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformation — arXiv:2609.37071},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37071},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_011079da189c; sha256 400707a335287f476f65ec274296359511579c18c0af1552e72aa5b7df0b3859},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37071. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Non-rigid point-cloud registration aims to find the corresponding target point for each point on a deforming source surface. Point-level matching keeps the full target cloud available, but correspondence becomes ambiguous when different regions have similar local geometry. Regional or coarse-to-fine methods provide broader spatial context, but an incorrect regional match can exclude the correct correspondence before dense matching. We propose CoCo-Reg, which uses regional patches to enrich dense point features without allowing patch predictions to restrict the final point-level search. CoCo-Reg constructs farthest-point-sampled patches, exchanges geometric information within and between source and target, supervises patch similarity using identity-corrected point overlap, and projects the resulting regional information back to dense point features. The final registration stage still scores the full target cloud before global point-level candidate selection. On 726 held-out ModelNet10 objects across nine deformation levels, two established learning-based baselines obtain mean correspondence errors of 0.1993 and 0.1921, whereas CoCo-Reg obtains 0.0547. Relative to its point-level baseline, this is a 72.6\% reduction. CoCo-Reg achieves lower correspondence error on 92.3\% of paired test objects and reduces the mean fraction of points with error above 0.1 from 47.3\% to 17.3\%. Chamfer distance and HD95 decrease in the same direction, and CoCo-Reg remains lower across all tested deformation levels. These results support using regional context for dense non-rigid correspondence without imposing a hard patch-level restriction on the final search. Because evaluation uses one checkpoint per method, the reported gains characterize the complete systems rather than the isolated causal contribution of an individual component. Code will be made publicly available.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37071 — 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 2026-10-07T18:04:24.813Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).