Metraipolis › archive › dc_72033509f905
Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models — arXiv:2609.33109
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33109
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:01:00.406Z
- SHA-256 of the archived text
cd6752b6b700febbe54a2071e3fc6013dce285f2a837b15621ba55b92ff4fc07- Stable URL of this page
https://metraipolis.com/documento/dc_72033509f905
How to cite
Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models — arXiv:2609.33109 — arXiv (en), https://arxiv.org/abs/2609.33109 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72033509f905 (Metraipolis archive dc_72033509f905, sha256 cd6752b6b700febbe54a2071e3fc6013dce285f2a837b15621ba55b92ff4fc07)
BibTeX
@misc{dc72033509f905,
title = {Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models — arXiv:2609.33109},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33109},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72033509f905; sha256 cd6752b6b700febbe54a2071e3fc6013dce285f2a837b15621ba55b92ff4fc07},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33109. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also require knowing how it is oriented. Although existing 3D VLMs may predict oriented boxes, box pose does not explicitly capture object-centric orientation or symmetry-induced ambiguities. We introduce orientation grounding, a referring grounding task that predicts an object's 6D orientation and axial symmetry from a language or box query in single-view or multi-view scenes. To support this task, we construct ReferOri, with 331K multi-view and 387K single-view orientation-grounding queries obtained through scalable reconstruction, consistency checking, and human verification. We further present OG-VLM, which adapts a 3D VLM with structured box/orientation outputs, sign and symmetry tokens, and geometry-aware auxiliary losses. Across single-view and multi-view benchmarks, OG-VLM substantially outperforms orientation-aware VLM baselines and surpasses object-level orientation foundation models on scene-level referring benchmarks, showing that explicit orientation grounding is a distinct and learnable capability beyond localization. Downstream results validate its benefit for orientation-related spatial reasoning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.33109 — 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 2026-10-07T20:29:02.543Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).