Metraipolis › archive › dc_4f083c8a7e94

BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration — arXiv:2609.11472

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11472
License (as archived)
CC0-1.0
Archived
2026-10-16T06:35:39.704Z
SHA-256 of the archived text
e826cbf0c83eadb8d15bfb6a3b948090f730ee18e2aa591d32bab52371e833fb
Stable URL of this page
https://metraipolis.com/documento/dc_4f083c8a7e94

How to cite

BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration — arXiv:2609.11472 — arXiv (en), https://arxiv.org/abs/2609.11472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f083c8a7e94 (Metraipolis archive dc_4f083c8a7e94, sha256 e826cbf0c83eadb8d15bfb6a3b948090f730ee18e2aa591d32bab52371e833fb)
BibTeX
@misc{dc4f083c8a7e94,
  title = {BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration — arXiv:2609.11472},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11472},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f083c8a7e94; sha256 e826cbf0c83eadb8d15bfb6a3b948090f730ee18e2aa591d32bab52371e833fb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable matching between partially observed, deforming point clouds requires global context and fine geometric detail. Coarse candidate selection can exclude correct fine-level correspondences. We present \paper, a unified conditional transport framework with the matching matrix itself as the evolving state. Coarse diffusion establishes global matching hypotheses; hierarchy-preserving lifting expands them into a structured high-resolution source. Geometry-conditioned ODE and SDE bridges continue refinement in the complete fine-level candidate space, allowing coarse errors to be corrected. The deterministic endpoint-parameterized conditional flow matching (CFM) design improves matching through iteration, while the SDE forward drift enables effective few-step refinement. Experiments on 4DMatch and 4DLoMatch demonstrate competitive matching and non-rigid registration, with transfer to CAPE and DeepDeform without target-domain training.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.11472 — 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 2026-10-16T06:06:28.784Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).