Metraipolis › archive › dc_50cdf7aa08b2

DMM-Align: Closed-Loop Optimization for 2D-3D Registration with Dual-Role Diffusion — arXiv:2609.27794

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27794
License (as archived)
CC0-1.0
Archived
2026-10-08T12:35:04.693Z
SHA-256 of the archived text
428a8ff3989f1af9645a48601e760bfa0ab63119ae3bfce9668a461b1ef6d44f
Stable URL of this page
https://metraipolis.com/documento/dc_50cdf7aa08b2

How to cite

DMM-Align: Closed-Loop Optimization for 2D-3D Registration with Dual-Role Diffusion — arXiv:2609.27794 — arXiv (en), https://arxiv.org/abs/2609.27794 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50cdf7aa08b2 (Metraipolis archive dc_50cdf7aa08b2, sha256 428a8ff3989f1af9645a48601e760bfa0ab63119ae3bfce9668a461b1ef6d44f)
BibTeX
@misc{dc50cdf7aa08b2,
  title = {DMM-Align: Closed-Loop Optimization for 2D-3D Registration with Dual-Role Diffusion — arXiv:2609.27794},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27794},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50cdf7aa08b2; sha256 428a8ff3989f1af9645a48601e760bfa0ab63119ae3bfce9668a461b1ef6d44f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27794. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

2D-3D registration remains brittle in challenging scenarios such as low overlap, occlusion, repetitive structures, and severe cross-modal ambiguity. A key reason is that existing methods improve representation learning, correspondence estimation, or pose computation in isolation, while the dominant failure mode is inherently cross-level, where errors propagate between features, correspondences, and pose. To address this limitation, we propose DMM-Align: Diffusion-based Matching Matrix Alignment, a closed-loop framework that couples correspondence refinement, pose estimation, and representation learning through a shared differentiable geometric state. Our method leverages diffusion in two coordinated roles: a geometry-aware diffusion process refines the soft matching matrix for robust correspondence estimation, while a geometry-conditioned diffusion teacher injects pose-induced supervision back into feature learning. These processes are connected via a differentiable geometric hinge that converts correspondences into a global pose and exposes geometric inconsistency to upstream modules. Extensive experiments on 7-Scenes and RGB-D Scenes V2 demonstrate that DMM-Align consistently outperforms strong baselines, especially under low-overlap and heavy-occlusion conditions, highlighting the effectiveness of closed-loop geometric feedback for robust 2D-3D registration.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.27794 — 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 2026-10-08T12:12:35.731Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).