mlsanityData to 7 Oct 2026

Find Any Part in 3D

arXiv 2411.13550 ↗First posted 20 Nov 2024cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Why don't we have foundation models in 3D yet? A key limitation is data scarcity. For 3D object part segmentation, existing datasets are small in size and lack diversity. We show that it is possible to break this data barrier by building a data engine powered by 2D foundation models. Our data engine automatically annotates any number of object parts: 1755x more unique part types than existing datasets combined. By training on our annotated data with a simple contrastive objective, we obtain an open-world model that generalizes to any part in any object based on any text query. Even when evaluated zero-shot, we outperform existing methods on the datasets they train on. We achieve 260% improvement in mIoU and boost speed by 6x to 300x. Our scaling analysis confirms that this generalization stems from the data scale, which underscores the impact of our data engine. Finally, to advance general-category open-world 3D part segmentation, we release a benchmark covering a wide range of objects and parts. Project website: https://ziqi-ma.github.io/find3dsite/

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 20 Nov 2024.

Builds on

32 of 43 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023Segment Anythingcited by 8,158
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  7. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  8. 2020Point Transformercited by 1,462
  9. 2021Grounded Language-Image Pre-trainingcited by 1,147
  10. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  11. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  12. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
20 more
  1. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  2. 2023LERF: Language Embedded Radiance Fieldscited by 538
  3. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  4. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  5. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  6. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  7. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  8. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  9. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  10. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 288
  11. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  12. 2023Distilled Feature Fields Enable Few-Shot Language-Guided Manipulationcited by 130
  13. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  14. 2024GARField: Group Anything with Radiance Fieldscited by 108
  15. 2024SAMPart3D: Segment Any Part in 3D Objectscited by 95
  16. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  17. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  18. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  19. 2023PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillationcited by 27
  20. 2020Cross-Shape Attention for Part Segmentation of 3D Point Cloudscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 18.

30 papers.

Sort:

By area:

  1. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 91
  2. 2025P3-SAM: Native 3D Part Segmentationcited by 39
  3. 2025UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulationcited by 23
  4. 2025Particulate: Feed-Forward 3D Object Articulationcited by 20
  5. 2025DexVLG: Dexterous Vision-Language-Grasp Model at Scalecited by 19
  6. 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 15
  7. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  8. 2026SegviGen: Repurposing 3D Generative Model for Part Segmentationcited by 9
  9. 2025SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materialscited by 5
  10. 2026PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understandingcited by 5
  11. 2026MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstructioncited by 5
  12. 2025Aligning Text, Images, and 3D Structure Token-by-Tokencited by 4
18 more
  1. 2026TORA: Topological Representation Alignment for 3D Shape Assemblycited by 4
  2. 2025Name That Part: 3D Part Segmentation and Namingcited by 3
  3. 2026Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detectioncited by 3
  4. 2026Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Controlcited by 2
  5. 2026Universal 3D Shape Matching via Coarse-to-Fine Language Guidancecited by 1
  6. 2026PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understandingcited by 1
  7. 2026EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learningcited by 1
  8. 2025OpenHuman4D: Open-Vocabulary 4D Human Parsingcited by 0
  9. 2025S2AM3D: Scale-controllable Part Segmentation of 3D Point Cloudscited by 0
  10. 2025XDen-1K: A Density Field Dataset of Real-World Objectscited by 0
  11. 2026CoSMo3D: Open-World Promptable 3D Semantic Part Segmentation through LLM-Guided Canonical Spatial Modelingcited by 0
  12. 2026Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshescited by 0
  13. 2026Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimationcited by 0
  14. 2026OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environmentscited by 0
  15. 2026MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshescited by 0
  16. 2026Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinementcited by 0
  17. 2026Articulated Object Reconstruction from Rest-State Observationcited by 0
  18. 2026UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interactioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model
  2. 2023OV-PARTS: Towards Open-Vocabulary Part Segmentation
  3. 2025Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation
  4. 2024OpenSU3D: Open World 3D Scene Understanding using Foundation Models
  5. 2024Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models
  6. 20243D Part Segmentation via Geometric Aggregation of 2D Visual Features
  7. 2025Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion
  8. 2023SAI3D: Segment Any Instance in 3D Scenes