Metraipolis › archive › dc_4c1decdf2b34

Generalizable 6D Pose Estimation of Textureless Objects with Planar-based Gaussian Splatting — arXiv:2609.07231

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07231
License (as archived)
CC0-1.0
Archived
2026-10-16T15:31:05.229Z
SHA-256 of the archived text
f1c4313dd95aa781163baaf4e33d36d07c4faa60acc4da336b662e5fa6ebf066
Stable URL of this page
https://metraipolis.com/documento/dc_4c1decdf2b34

How to cite

Generalizable 6D Pose Estimation of Textureless Objects with Planar-based Gaussian Splatting — arXiv:2609.07231 — arXiv (en), https://arxiv.org/abs/2609.07231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4c1decdf2b34 (Metraipolis archive dc_4c1decdf2b34, sha256 f1c4313dd95aa781163baaf4e33d36d07c4faa60acc4da336b662e5fa6ebf066)
BibTeX
@misc{dc4c1decdf2b34,
  title = {Generalizable 6D Pose Estimation of Textureless Objects with Planar-based Gaussian Splatting — arXiv:2609.07231},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07231},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4c1decdf2b34; sha256 f1c4313dd95aa781163baaf4e33d36d07c4faa60acc4da336b662e5fa6ebf066},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Estimating the 6D pose of textureless objects without prior CAD models remains a critical challenge due to the lack of appearance features. While recent generalizable approaches alleviate the dependence on object-specific models, their performance on low-texture objects is often limited by insufficient geometric constraints in the underlying representations. In this work, we propose PG-Pose, a geometry-aware framework combining Planar-based Gaussian Splatting (PGS) reconstruction and Geometry-driven pose optimization. In the offline representation extraction stage, three distinct representations of the object are extracted from multi-view reference RGB images with known poses. PG-Pose reconstructs a 3D Gaussian representation and renders high-fidelity depth maps to generate 3D point clouds through back projection. In the online pose inference stage, the initial pose of the input image is estimated by 2D-3D correspondence matching between the input image and the reconstructed 3D point clouds, followed by a PGS-Refiner for iterative pose optimization. Evaluations on the OnePose-LowTexture datasets, PG-Pose achieves an average accuracy of 94.2% ADD(S)@0.1d, with a 2.1% improvement average accuracy compared with the state-of-the-art (SOTA) GS-based approach. To further demonstrate the effectiveness of PG-Pose for industrial robots in grasping tasks, we deploy it on a dual-arm industrial robot and successfully realize the grasping task on an unseen object.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.07231 — 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 2026-10-16T15:11:47.577Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).