mlsanityData to 14 Oct 2026

SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM

arXiv 2603.23386 ↗First posted 24 Mar 2026cs.CV cs.GR cs.ROcited by 5

Not on the map. Why?

Abstract (arXiv)

High-quality articulated 3D assets are indispensable for embodied AI and physical simulation, yet 3D generation still focuses on static meshes, leaving a gap in "sim-ready" interactive objects. Most recent articulated object creation methods rely on multi-stage pipelines that accumulate errors across decoupled modules. Alternatively, unified MLLMs offer a single-stage path to joint static asset understanding and sim-ready asset generation. However dense voxel-based 3D tokenization yields long 3D token sequences and high memory overhead, limiting scalability to complex articulated objects. To address this, we propose SIMART, a unified MLLM framework that jointly performs part-level decomposition and kinematic prediction. By introducing a Sparse 3D VQ-VAE, SIMART reduces token counts by 70% vs. dense voxel tokens, enabling high-fidelity multi-part assemblies. SIMART achieves state-of-the-art performance on PartNet-Mobility and in-the-wild AIGC datasets, and enables physics-based robotic simulation.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 53 of its 59 references that are in the map. First posted on arXiv 24 Mar 2026.

Builds on

53 of 59 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2025Qwen3-VL Technical Reportcited by 2,793
  6. 2025DINOv3cited by 1,414
  7. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  8. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  9. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  10. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  11. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  12. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
38 more
  1. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
  2. 2025SAM 3D: 3Dfy Anything in Imagescited by 247
  3. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 156
  4. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 125
  5. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 118
  6. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 111
  7. 2024Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Modelcited by 96
  8. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 95
  9. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generationcited by 82
  10. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  11. 2024Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objectscited by 69
  12. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
  13. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  14. 2021UMPNet: Universal Manipulation Policy Network for Articulated Objectscited by 65
  15. 2024Advances in 3D Generation: A Surveycited by 63
  16. 2023CAGE: Controllable Articulation GEnerationcited by 52
  17. 2024Robo-GS: A Physics Consistent Spatial-Temporal Model for Robotic Arm with Hybrid Representationcited by 46
  18. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 43
  19. 2025P3-SAM: Native 3D Part Segmentationcited by 43
  20. 2025PhysX-3D: Physical-Grounded 3D Asset Generationcited by 42
  21. 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 41
  22. 2025LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPScited by 41
  23. 2024Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Roboticscited by 40
  24. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 38
  25. 2025PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Imagecited by 37
  26. 2025ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splattingcited by 35
  27. 2025DRAWER: Digital Reconstruction and Articulation With Environment Realismcited by 29
  28. 2024Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesiscited by 24
  29. 2025Particulate: Feed-Forward 3D Object Articulationcited by 23
  30. 2024Mani-GS: Gaussian Splatting Manipulation with Triangular Meshcited by 22
  31. 2025DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Datacited by 21
  32. 2025URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Modelcited by 21
  33. 2025MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Meshcited by 20
  34. 2025Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generationcited by 19
  35. 2024SLGaussian: Fast Language Gaussian Splatting in Sparse Viewscited by 18
  36. 2024LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understandingcited by 17
  37. 2025ArtVIP: Articulated Digital Assets of Visual Realism, Modular Interaction, and Physical Fidelity for Robot Learningcited by 16
  38. 2025PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Modelcited by 15

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assetscited by 1
  2. 2026NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulationcited by 1
  3. 2026LEGO-Anything: Coding Agents for 3D Scene Reconstructioncited by 0
  4. 2026EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulationcited by 0
  5. 2026Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmarkcited by 0