Metraipolis › archive › dc_9e2f94eb118d
ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement — arXiv:2608.16011
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16011
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:58:53.695Z
- SHA-256 of the archived text
dfaa7596cb968c6b4fb7f8c1c282524586fac4e3c4380f1a1e7aa9b1ff65d5b6- Stable URL of this page
https://metraipolis.com/documento/dc_9e2f94eb118d
How to cite
ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement — arXiv:2608.16011 — arXiv (en), https://arxiv.org/abs/2608.16011 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9e2f94eb118d (Metraipolis archive dc_9e2f94eb118d, sha256 dfaa7596cb968c6b4fb7f8c1c282524586fac4e3c4380f1a1e7aa9b1ff65d5b6)
BibTeX
@misc{dc9e2f94eb118d,
title = {ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement — arXiv:2608.16011},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16011},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9e2f94eb118d; sha256 dfaa7596cb968c6b4fb7f8c1c282524586fac4e3c4380f1a1e7aa9b1ff65d5b6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16011. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce ReRef-3D, a benchmark for language-guided placement in 3D scenes. It contains 33,826 instructions across 998 CLEVR-derived scenes, spanning 16 placement families and direct, one-hop, and two-hop references. Each instruction must be resolved into a valid new placement position. Given that an instruction defines a region of acceptable placements rather than one coordinate, our evaluation inserts a prediction into the scene, recomputes relations, and tests relation satisfaction and physical validity. Each instruction also includes a verified naturalized rewrite. After fine-tuning, LLaVA-3D, 3D-LLM, and PlaceIt3D produce valid placements for 68.3%, 31.6%, and 22.4% of instructions, respectively. Across models, relation satisfaction surpasses physical validity, relations such as nearest and between are the most difficult, and phrasing has minimal effect on performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.16011 — 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 2026-10-18T18:06:57.877Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).