UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
Published 14 Sept 2026arXiv:2609.12898
Updated 2 h ago · first seen 14 Sept 2026
paper_01M2F500T1VC40RQBZJHFF7FWT
Abstract
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.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 2
- Property changedPaperUniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - New paperPaperUniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
New paper: UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
arxiv
Sources
Sources 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.