mlsanityData to 14 Oct 2026

AKB-48: A Real-World Articulated Object Knowledge Base

arXiv 2202.08432 ↗First posted 17 Feb 2022cs.CVcited by 82

Not on the map. Why?

Abstract (arXiv)

Human life is populated with articulated objects. A comprehensive understanding of articulated objects, namely appearance, structure, physics property, and semantics, will benefit many research communities. As current articulated object understanding solutions are usually based on synthetic object dataset with CAD models without physics properties, which prevent satisfied generalization from simulation to real-world applications in visual and robotics tasks. To bridge the gap, we present AKB-48: a large-scale Articulated object Knowledge Base which consists of 2,037 real-world 3D articulated object models of 48 categories. Each object is described by a knowledge graph ArtiKG. To build the AKB-48, we present a fast articulation knowledge modeling (FArM) pipeline, which can fulfill the ArtiKG for an articulated object within 10-15 minutes, and largely reduce the cost for object modeling in the real world. Using our dataset, we propose AKBNet, a novel integral pipeline for Category-level Visual Articulation Manipulation (C-VAM) task, in which we benchmark three sub-tasks, namely pose estimation, object reconstruction and manipulation. Dataset, codes, and models will be publicly available at https://liuliu66.github.io/articulationobjects/.

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

23 of 33 references.

References · 23

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2017Hindsight Experience Replaycited by 1,136
  6. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  7. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  8. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  9. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  10. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 182
  11. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 165
  12. 2019Category-Level Articulated Object Pose Estimationcited by 159
11 more
  1. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 119
  2. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  3. 2020ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theorycited by 70
  4. 2018Deep Part Induction from Articulated Object Pairscited by 66
  5. 2021Towards Real-World Category-level Articulation Pose Estimationcited by 39
  6. 2020Visual Identification of Articulated Object Partscited by 37
  7. 2018The RBO Dataset of Articulated Objects and Interactionscited by 34
  8. 2017Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lightingcited by 31
  9. 2020Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimationcited by 25
  10. 2020Sim2Real2Sim: Bridging the Gap Between Simulation and Real-World in Flexible Object Manipulationcited by 14
  11. 2018Applying Domain Randomization to Synthetic Data for Object Category Detectioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 19; 2024: 21; 2025: 24; 2026: 13.

82 papers.

Sort:

By area:

  1. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  2. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  3. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 139
  4. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 118
  5. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 111
  6. 2022Full-Body Articulated Human-Object Interactioncited by 78
  7. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
  8. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  9. 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objectscited by 64
  10. 2023Grounding 3D Object Affordance from 2D Interactions in Imagescited by 62
  11. 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 58
  12. 2022OPD: Single-view 3D Openable Part Detectioncited by 54
38 more
  1. 2023CAGE: Controllable Articulation GEnerationcited by 52
  2. 2023LEMON: Learning 3D Human-Object Interaction Relation from 2D Imagescited by 49
  3. 2023OPDMulti: Openable Part Detection for Multiple Objectscited by 39
  4. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 35
  5. 2024DragAPart: Learning a Part-Level Motion Prior for Articulated Objectscited by 32
  6. 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generationcited by 30
  7. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  8. 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understandingcited by 26
  9. 2023NAP: Neural 3D Articulation Priorcited by 25
  10. 2024Learning 2D Invariant Affordance Knowledge for 3D Affordance Groundingcited by 22
  11. 2024GarmentLab: A Unified Simulation and Benchmark for Garment Manipulationcited by 22
  12. 2023Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMscited by 19
  13. 2025Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generationcited by 19
  14. 2023Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterpartscited by 18
  15. 2023ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentationcited by 18
  16. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 18
  17. 2023GarmentTracking: Category-Level Garment Pose Trackingcited by 16
  18. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  19. 2023Visual-Tactile Sensing for In-Hand Object Reconstructioncited by 13
  20. 2025Detection Based Part-level Articulated Object Reconstruction from Single RGBD Imagecited by 13
  21. 2025SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splattingcited by 13
  22. 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learningcited by 12
  23. 2023PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environmentscited by 11
  24. 2025IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environmentscited by 11
  25. 2024Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Descriptioncited by 9
  26. 2025Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objectscited by 9
  27. 2025Towards Scalable Spatial Intelligence via 2D-to-3D Data Liftingcited by 8
  28. 2023Primitive-based 3D Human-Object Interaction Modelling and Programmingcited by 7
  29. 2025Digital Twin Generation from Visual Data: A Surveycited by 7
  30. 2023RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulationcited by 6
  31. 2024ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualizationcited by 6
  32. 2024Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotationscited by 6
  33. 2024SM3: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objectscited by 5
  34. 2024Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Imagescited by 5
  35. 2024Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objectscited by 5
  36. 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Imagecited by 5
  37. 2022Structure from Action: Learning Interactions for Articulated Object 3D Structure Discoverycited by 4
  38. 2023UniG3D: A Unified 3D Object Generation Datasetcited by 4

50 most cited of 82 All 82 (JSON)