mlsanityData to 7 Oct 2026

UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction

arXiv 2609.12898 ↗First posted 11 Sep 2026cs.CV cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 73 of its 86 references that are in the map. First posted on arXiv 11 Sep 2026.

Builds on

73 of 86 references.

References · 73

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2023Segment Anythingcited by 8,158
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  11. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  12. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
38 more
  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  2. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  3. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  5. 2020Point Transformercited by 1,462
  6. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  7. 2021Grounded Language-Image Pre-trainingcited by 1,147
  8. 2025OpenAI GPT-5 System Cardcited by 910
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  10. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  11. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  12. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  13. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  14. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  15. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  16. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  17. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  18. 2023Learning Interactive Real-World Simulatorscited by 440
  19. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  20. 2023LangSplat: 3D Language Gaussian Splattingcited by 410
  21. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  22. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  23. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 288
  24. 2021Voxel Transformer for 3D Object Detectioncited by 247
  25. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 242
  26. 2021Group-Free 3D Object Detection via Transformerscited by 215
  27. 2024RT-H: Action Hierarchies Using Languagecited by 204
  28. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  29. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  30. 2022PLA: Language-Driven Open-Vocabulary 3D Scene Understandingcited by 176
  31. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  32. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 157
  33. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 151
  34. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  35. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  36. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
  37. 2024MOKA: Open-World Robotic Manipulation through Mark-Based Visual Promptingcited by 126
  38. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117

50 most cited of 73 All 73 (JSON)

Built on by

Not cited yet.