الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Yu, X., Qi, Z., He, J., Zhang, W., Chen, X., Yao, G., Yi, L., Zhang, Z., & Wang, H. (2026). UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction. https://omanscience.com/ar/articles/unipart-towards-zero-shot-language-grounded-3d-part-segmentation-for-embodied-interaction
MLA 9
Yu, Xinqiang, et al. "UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction." https://omanscience.com/ar/articles/unipart-towards-zero-shot-language-grounded-3d-part-segmentation-for-embodied-interaction.
شيكاغو (المؤلف–التاريخ)
Yu, Xinqiang, Zekun Qi, Jiawei He, Wenyao Zhang, Xuchuan Chen, Guaocai Yao, Li Yi, Zhaoxiang Zhang, and He Wang. 2026. "UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction." https://omanscience.com/ar/articles/unipart-towards-zero-shot-language-grounded-3d-part-segmentation-for-embodied-interaction.
هارفارد
Yu, X., Qi, Z., He, J., Zhang, W., Chen, X., Yao, G., Yi, L., Zhang, Z. and Wang, H. (2026) 'UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction', Available at: https://omanscience.com/ar/articles/unipart-towards-zero-shot-language-grounded-3d-part-segmentation-for-embodied-interaction.
فانكوفر
Yu X, Qi Z, He J, Zhang W, Chen X, Yao G, et al. UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction. https://omanscience.com/ar/articles/unipart-towards-zero-shot-language-grounded-3d-part-segmentation-for-embodied-interaction
IEEE
X. Yu, Z. Qi, J. He, W. Zhang, X. Chen, G. Yao, L. Yi, Z. Zhang, and H. Wang, "UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction," https://omanscience.com/ar/articles/unipart-towards-zero-shot-language-grounded-3d-part-segmentation-for-embodied-interaction.