Metraipolis › archive › dc_9be52d0833df
CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images — arXiv:2608.05569
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05569
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:35:59.787Z
- SHA-256 of the archived text
910c4be91432b79e0f1a7ef306e97387bb782dc3d92d750f04b4a7bdb6bfcaa4- Stable URL of this page
https://metraipolis.com/documento/dc_9be52d0833df
How to cite
CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images — arXiv:2608.05569 — arXiv (en), https://arxiv.org/abs/2608.05569 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9be52d0833df (Metraipolis archive dc_9be52d0833df, sha256 910c4be91432b79e0f1a7ef306e97387bb782dc3d92d750f04b4a7bdb6bfcaa4)
BibTeX
@misc{dc9be52d0833df,
title = {CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images — arXiv:2608.05569},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05569},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9be52d0833df; sha256 910c4be91432b79e0f1a7ef306e97387bb782dc3d92d750f04b4a7bdb6bfcaa4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05569. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multiview image-based 3D visual grounding predicts a coordinate frame to define a coordinate system and then regresses a 3D bounding box for localization. However, existing methods jointly optimize coordinate frame selection and box regression, leading to coordinate-relative box ambiguity and degraded grounding performance. This ambiguity arises because the same box admits different numerical representations across coordinate frames, creating multiple optimization targets and yielding invalid compromise predictions. To tackle this challenge, we propose CoordRefer, a coordinate-aware framework that decouples coordinate frame selection from coordinate-conditioned grounding. CoordRefer first selects a reference frame to define the coordinate system and then conditions 3D box prediction on the coordinate system. We perform coordinate-aware supervised fine-tuning to establish coordinate frame selection and coordinate-conditioned box regression, followed by Group Relative Policy Optimization with 3D IoU-based rewards to align both stages with downstream grounding quality. On ScanRefer with Qwen3-VL-2B, CoordRefer achieves gains of 11% in [email protected] and 7% in [email protected] over the coordinate-agnostic baseline, while its geometrically refined variant surpasses methods using explicit 3D inputs. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05569 — 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 2026-10-31T10:23:30.983Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).