Metraipolis › archive › dc_034ac0855d93

Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Features — arXiv:2609.06726

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06726
License (as archived)
CC0-1.0
Archived
2026-10-16T15:09:23.112Z
SHA-256 of the archived text
045e4f22cfc49681601d8711fa8a102c3d0b3c4141f2361e18d4a556509d5127
Stable URL of this page
https://metraipolis.com/documento/dc_034ac0855d93

How to cite

Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Features — arXiv:2609.06726 — arXiv (en), https://arxiv.org/abs/2609.06726 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_034ac0855d93 (Metraipolis archive dc_034ac0855d93, sha256 045e4f22cfc49681601d8711fa8a102c3d0b3c4141f2361e18d4a556509d5127)
BibTeX
@misc{dc034ac0855d93,
  title = {Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Features — arXiv:2609.06726},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06726},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_034ac0855d93; sha256 045e4f22cfc49681601d8711fa8a102c3d0b3c4141f2361e18d4a556509d5127},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06726. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision transformer as its only pretrained component within the pose estimation pipeline, B2TFPose extracts dense patch-level features that generalize across the synthetic-to-real domain gap without any task-specific fine-tuning, revisiting the classical local feature matching paradigm through the lens of large-scale self-supervised foundation models. Three contributions advance the training-free state of the art. A geodesic non-maximum suppression strategy retrieves a viewpoint-diverse template set for coarse-to-fine correspondence matching. Render-guided Re-Correspondence (RRC) synthesizes object-specific views at the estimated pose and re-establishes dense 2D-3D correspondences to sharpen the initial estimate without additional learned parameters. A multi-mask hypothesis selection strategy jointly scores competing segmentation candidates to resolve segmentation ambiguity. On the seven core datasets of the BOP Benchmark, B2TFPose achieves 40.7 mean AR without refinement and 56.4 with refinement, establishing state-of-the-art performance among training-free RGB methods and outperforming trained counterparts including GigaPose and GenFlow, at competitive inference speed.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.06726 — 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 2026-10-16T14:49:57.122Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).