Metraipolis › archive › dc_e277b01bd225

GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking — arXiv:2609.39116

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39116
License (as archived)
CC0-1.0
Archived
2026-10-07T14:45:50.318Z
SHA-256 of the archived text
d619ee658013770f077725542bba6fa1edf0b79cf4d2064f02482660b5d93af7
Stable URL of this page
https://metraipolis.com/documento/dc_e277b01bd225

How to cite

GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking — arXiv:2609.39116 — arXiv (en), https://arxiv.org/abs/2609.39116 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e277b01bd225 (Metraipolis archive dc_e277b01bd225, sha256 d619ee658013770f077725542bba6fa1edf0b79cf4d2064f02482660b5d93af7)
BibTeX
@misc{dce277b01bd225,
  title = {GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking — arXiv:2609.39116},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39116},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e277b01bd225; sha256 d619ee658013770f077725542bba6fa1edf0b79cf4d2064f02482660b5d93af7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39116. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Prior-free 6D object pose tracking seeks to recover the trajectory of an unseen object from a single RGB video without object-specific CAD models, posed reference images, or pose annotations. Geometric foundation models provide complementary object-centric and scene-centric cues, yet SAM3D CAD is indexed by an arbitrary object-local surface parameterization, whereas reconstructed evidence is expressed in a sequence-specific world frame with partial surface coverage. To exploit this complementarity, we formulate tracking as generation-reconstruction correspondence and introduce GRC-Pose, a correspondence-based framework that combines learned correspondence prediction with robust pose estimation. Concretely, GeoCorr-Matcher estimates weighted object-scene correspondences and per-match uncertainty for each pose candidate. FGH-Solver integrates these matches through multiple robust geometric estimators and sequence-level posterior inference, while a posterior-gated memory retains only inlier-supported observations through occlusion and viewpoint change. Extensive evaluation shows that with SAM3D CAD, GRC-Pose achieves state-of-the-art Average Recall and motion retention on HOT3D, improving the latter by 58% over prior art. On classical benchmarks including YCBInEOAT and LINEMOD, it remains highly competitive.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39116 — 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 2026-10-07T14:19:00.674Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).