mlsanityData to 7 Oct 2026

PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

arXiv 1812.02713 ↗First posted 6 Dec 2018cs.CVcited by 521

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a novel method for part instance segmentation and demonstrate its superior performance over existing methods.

Key facts. Cited by 521 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 71; 2022: 76; 2023: 90; 2024: 107; 2025: 91; 2026: 86.

521 papers.

Sort:

By area:

  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  2. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  3. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  4. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  5. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  6. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  7. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  8. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  9. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  10. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  11. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 216
  12. 2021Concealed Object Detectioncited by 212
38 more
  1. 2023Scalable 3D Captioning with Pretrained Modelscited by 201
  2. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  3. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  4. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  5. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 157
  6. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 152
  7. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  8. 2023Weakly Supervised 3D Open-vocabulary Segmentationcited by 133
  9. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  10. 2024SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understandingcited by 130
  11. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  12. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 117
  13. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  14. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  15. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 115
  16. 2024GARField: Group Anything with Radiance Fieldscited by 108
  17. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  18. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  19. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 106
  20. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  21. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 102
  22. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  23. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  24. 2024SAMPart3D: Segment Any Part in 3D Objectscited by 95
  25. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  26. 2023Unified Human-Scene Interaction via Prompted Chain-of-Contactscited by 91
  27. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 91
  28. 2024Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Modelcited by 90
  29. 2023OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentationcited by 82
  30. 2022AKB-48: A Real-World Articulated Object Knowledge Basecited by 81
  31. 2024General Flow as Foundation Affordance for Scalable Robot Learningcited by 80
  32. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
  33. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
  34. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
  35. 2022Full-Body Articulated Human-Object Interactioncited by 76
  36. 2023OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learningcited by 75
  37. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  38. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66

50 most cited of 521 All 521 (JSON)