mlsanityData to 7 Oct 2026

PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models

arXiv 2212.01558 ↗First posted 3 Dec 2022cs.CV cs.ROcited by 117

Not on the map. Why?

Abstract (arXiv)

Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). Builds on 70 of its 84 references that are in the map. First posted on arXiv 3 Dec 2022.

Builds on

70 of 84 references.

References · 70

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2021Grounded Language-Image Pre-trainingcited by 1,147
  11. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  12. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
38 more
  1. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  2. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  3. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  4. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  5. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  6. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  7. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  8. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  9. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  10. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 332
  13. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  14. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  15. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  16. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  17. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  18. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  19. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  20. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  21. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  22. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 145
  23. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  24. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  25. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  26. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  27. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  28. 2019BlenderProccited by 76
  29. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  30. 2019StructureNet: Hierarchical Graph Networks for 3D Shape Generationcited by 59
  31. 2022AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatarscited by 55
  32. 2019Point Cloud Instance Segmentation using Probabilistic Embeddingscited by 52
  33. 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
  34. 2021Language Grounding with 3D Objectscited by 43
  35. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  36. 2021ClipMatrix: Text-controlled Creation of 3D Textured Meshescited by 40
  37. 2022Text and Image Guided 3D Avatar Generation and Manipulationcited by 35
  38. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 31

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 19; 2024: 29; 2025: 33; 2026: 36.

117 papers.

Sort:

By area:

  1. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  2. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  3. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  4. 2023Segment Any 3D Gaussianscited by 158
  5. 2024SAMPart3D: Segment Any Part in 3D Objectscited by 95
  6. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 91
  7. 2023CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIPcited by 89
  8. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  9. 2023Segment Anything in 3D with Radiance Fieldscited by 61
  10. 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 60
  11. 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 60
  12. 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 57
38 more
  1. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
  2. 2025Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registrationcited by 50
  3. 2024Point-SAM: Promptable 3D Segmentation Model for Point Cloudscited by 49
  4. 2024Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databasescited by 43
  5. 2025X-Part: high fidelity and structure coherent shape decompositioncited by 42
  6. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 41
  7. 2025P3-SAM: Native 3D Part Segmentationcited by 39
  8. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  9. 2024Segment Any Meshcited by 37
  10. 2023Zero-Shot 3D Shape Correspondencecited by 33
  11. 2023EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understandingcited by 33
  12. 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
  13. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  14. 2024Learning Generalizable Feature Fields for Mobile Manipulationcited by 31
  15. 2024Search3D: Hierarchical Open-Vocabulary 3D Segmentationcited by 31
  16. 2024Find Any Part in 3Dcited by 30
  17. 2023PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillationcited by 27
  18. 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understandingcited by 24
  19. 2024MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesiscited by 22
  20. 2024S2O: Static to Openable Enhancement for Articulated 3D Objectscited by 22
  21. 2024Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environmentscited by 21
  22. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  23. 2025Particulate: Feed-Forward 3D Object Articulationcited by 20
  24. 2025DexVLG: Dexterous Vision-Language-Grasp Model at Scalecited by 19
  25. 2023ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentationcited by 18
  26. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  27. 2024No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentationcited by 18
  28. 2026Utonia: Toward One Encoder for All Point Cloudscited by 18
  29. 2023Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Featurescited by 17
  30. 2024Composable Part-Based Manipulationcited by 17
  31. 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programscited by 15
  32. 20243D Part Segmentation via Geometric Aggregation of 2D Visual Featurescited by 15
  33. 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Cloudscited by 15
  34. 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 15
  35. 2024iSeg: Interactive 3D Segmentation via Interactive Attentioncited by 14
  36. 2025VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibilitycited by 11
  37. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  38. 20243x2: 3D Object Part Segmentation by 2D Semantic Correspondencescited by 10

50 most cited of 117 All 117 (JSON)