Metraipolis › archive › dc_3b445ae4bb43
UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction — arXiv:2609.12898
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12898
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:40.884Z
- SHA-256 of the archived text
d9ed66f9228e6c6e655c07e3f141d88ebfd6ff5a918979a5010bbb4dee0b5336- Stable URL of this page
https://metraipolis.com/documento/dc_3b445ae4bb43
How to cite
UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction — arXiv:2609.12898 — arXiv (en), https://arxiv.org/abs/2609.12898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3b445ae4bb43 (Metraipolis archive dc_3b445ae4bb43, sha256 d9ed66f9228e6c6e655c07e3f141d88ebfd6ff5a918979a5010bbb4dee0b5336)
BibTeX
@misc{dc3b445ae4bb43,
title = {UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction — arXiv:2609.12898},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12898},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3b445ae4bb43; sha256 d9ed66f9228e6c6e655c07e3f141d88ebfd6ff5a918979a5010bbb4dee0b5336},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized but object-aware, or part-aware but limited to closed-set taxonomies, which weakens zero-shot transfer. We study text-conditioned 3D part segmentation, where a free-form phrase selects a functional part on point cloud. We introduce UniPart, a feed-forward cross-modal 3D Transformer that conditions CLIP text embedding. To scale supervision, we build LangPart-1M with 160K+ Objaverse assets and 8M text to part pairs using multi-view consistent part generation. We further manually label a high-quality subset, LangPart-4K, for fine-tuning and evaluation. UniPart achieves strong zero-shot results on open-vocabulary part benchmarks and transfers to language-conditioned part grasping in real world. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.12898 — 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 2026-10-16T02:51:27.953Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).