mlsanityData to 14 Oct 2026

Particulate: Feed-Forward 3D Object Articulation

arXiv 2512.11798 ↗First posted 12 Dec 2025cs.CV cs.AI cs.GRcited by 23

Not on the map. Why?

Abstract (arXiv)

We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion constraints. The model is based on a transformer network, the Part Articulation Transformer, which predicts all these parameters for all joints. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate maps the output of the network back to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate also works on AI-generated 3D assets, enabling the generation of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D model. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Empirically, Particulate significantly outperforms state-of-the-art approaches.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 65 of its 70 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

65 of 70 references.

References · 65

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2023Segment Anythingcited by 8,234
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  10. 2021Grounded Language-Image Pre-trainingcited by 1,156
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  12. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
38 more
  1. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  2. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  3. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  4. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  5. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
  6. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 156
  7. 2020iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenescited by 155
  8. 2024BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulationcited by 148
  9. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 139
  10. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 137
  11. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 137
  12. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  13. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 118
  14. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 118
  15. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  16. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  17. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 98
  18. 2024SAMPart3D: Segment Any Part in 3D Objectscited by 97
  19. 2024Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Modelcited by 96
  20. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 95
  21. 2024Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objectscited by 69
  22. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
  23. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  24. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  25. 2024Learning the 3D Fauna of the Webcited by 59
  26. 2024GRUtopia: Dream General Robots in a City at Scalecited by 59
  27. 2023CAGE: Controllable Articulation GEnerationcited by 52
  28. 2022Self-supervised Neural Articulated Shape and Appearance Modelscited by 51
  29. 2025RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assetscited by 47
  30. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  31. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 43
  32. 2025MagicArticulate: Make Your 3D Models Articulation-Readycited by 43
  33. 2025P3-SAM: Native 3D Part Segmentationcited by 43
  34. 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 41
  35. 2023Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusioncited by 38
  36. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  37. 2024Segment Any Meshcited by 37
  38. 2024DragAPart: Learning a Part-Level Motion Prior for Articulated Objectscited by 32

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 23.

23 papers.

Sort:

By area:

  1. 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generationcited by 30
  2. 2026SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLMcited by 5
  3. 2026Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Controlcited by 4
  4. 2026AniGen: Unified S3 Fields for Animatable 3D Asset Generationcited by 3
  5. 2026ViPS: Video-informed Pose Spaces for Auto-Rigged Meshescited by 3
  6. 2026UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assetscited by 2
  7. 20263D Generation for Embodied AI and Robotic Simulation: A Surveycited by 1
  8. 2026Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learningcited by 1
  9. 2026UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Imagecited by 1
  10. 2026PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assetscited by 1
  11. 2026Visual General Intelligence: A White Papercited by 1
  12. 2026AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videoscited by 1
11 more
  1. 2026Lookalike3D: Seeing Double in 3Dcited by 0
  2. 2026Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generationcited by 0
  3. 2026Functionalization via Structure Completion and Motion Rectificationcited by 0
  4. 2026ArtiMo: Agent-Driven Articulated Mesh Animationcited by 0
  5. 2026FunArt: Decoding Functional Structure and Articulation from Generative 3D Latentscited by 0
  6. 2026FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observationscited by 0
  7. 2026Track2Art: Articulated Object Model Recovery with Visual-Geometric Track Representationscited by 0
  8. 2026ArticulateArena: A Metric for Articulated Kinematicscited by 0
  9. 2026ArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single Imagecited by 0
  10. 2026Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmarkcited by 0
  11. 2026ViewStruct: View-Grounded Articulation and Connectivity Inferencecited by 0