mlsanityData to 14 Oct 2026

Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation

arXiv 2503.13424 ↗First posted 17 Mar 2025cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Large-scale articulated objects with high quality are desperately needed for multiple tasks related to embodied AI. Most existing methods for creating articulated objects are either data-driven or simulation based, which are limited by the scale and quality of the training data or the fidelity and heavy labour of the simulation. In this paper, we propose Infinite Mobility, a novel method for synthesizing high-fidelity articulated objects through procedural generation. User study and quantitative evaluation demonstrate that our method can produce results that excel current state-of-the-art methods and are comparable to human-annotated datasets in both physics property and mesh quality. Furthermore, we show that our synthetic data can be used as training data for generative models, enabling next-step scaling up. Code is available at https://github.com/Intern-Nexus/Infinite-Mobility

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 30 of its 36 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

30 of 36 references.

References · 30

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  2. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  3. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  4. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  5. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  6. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  7. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  8. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  9. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 156
  10. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  11. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 147
  12. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 137
18 more
  1. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 119
  2. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 118
  3. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 111
  4. 2024Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Modelcited by 96
  5. 2022AKB-48: A Real-World Articulated Object Knowledge Basecited by 82
  6. 2020ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theorycited by 70
  7. 2024Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objectscited by 69
  8. 2024Real2Code: Reconstruct Articulated Objects via Code Generationcited by 69
  9. 2024ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactionscited by 57
  10. 2022CLA-NeRF: Category-Level Articulated Neural Radiance Fieldcited by 56
  11. 2023CAGE: Controllable Articulation GEnerationcited by 52
  12. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  13. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 43
  14. 2024Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesiscited by 24
  15. 20233D Implicit Transporter for Temporally Consistent Keypoint Discoverycited by 20
  16. 2023Template-free Articulated Neural Point Clouds for Reposable View Synthesiscited by 15
  17. 2024MineStudio: A Streamlined Package for Minecraft AI Agent Developmentcited by 13
  18. 2024RoCap: A Robotic Data Collection Pipeline for the Pose Estimation of Appearance-Changing Objectscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 14.

19 papers.

Sort:

By area:

  1. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 50
  2. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 50
  3. 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understandingcited by 26
  4. 2025Particulate: Feed-Forward 3D Object Articulationcited by 23
  5. 2026PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual Worldcited by 9
  6. 2026ArtLLM: Generating Articulated Assets via 3D LLMcited by 8
  7. 2026SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLMcited by 5
  8. 2026Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objectscited by 4
  9. 2026Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Controlcited by 4
  10. 2025ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenescited by 3
  11. 2026SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Trackingcited by 3
  12. 2025RealAppliance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manualscited by 2
7 more
  1. 20263D Generation for Embodied AI and Robotic Simulation: A Surveycited by 1
  2. 2026NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulationcited by 1
  3. 2026DailyArt: Discovering Articulation from Single Static Images via Latent Dynamicscited by 0
  4. 2026MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modelingcited by 0
  5. 2026KaiNinja: Extending Native 3D Generators to the Part Levelcited by 0
  6. 2026MoSE3: Learning World-Space SE(3) at Every Pixelcited by 0
  7. 2026Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmarkcited by 0