You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A curated list of papers, datasets, benchmarks, simulators, and evaluation resources for 3D generation in embodied AI and robotic simulation.
This repository accompanies our survey on 3D generation for embodied AI and robotic simulation. It organizes the literature around how generative 3D methods support embodied systems, from simulation-ready asset creation, to interactive scene generation, to sim-to-real transfer. In addition to research papers, we collect resources that are useful for building and evaluating embodied 3D generation systems, including datasets, benchmarks, simulator platforms, and asset formats.
Contributions are welcome. Please open an issue or submit a pull request if you would like to add a paper, dataset, benchmark, simulator, or evaluation resource.
Highlights
Survey-driven taxonomy for 3D generation in embodied AI
Curated coverage of papers, datasets, benchmarks, simulators, and evaluation
Emphasis on simulation-ready assets and environments rather than visual realism alone
We focus on 3D generation methods that are useful for embodied AI, robot learning, and robotic simulation. Compared with general-purpose 3D generation, embodied settings require more than visual realism: generated assets and environments should be executable, physically meaningful, interactive, and compatible with simulation platforms.
We organize the field into three major roles:
Data Generator: generating simulation-ready objects and assets, including articulated, physically grounded, and deformable content.
Simulation Environments: generating interactive, controllable, and task-oriented 3D scenes for embodied training and evaluation.
Sim2Real Bridge: using 3D generation for digital twins, data augmentation, and synthetic demonstrations to support transfer to real robots.
Awesome List
In chronological order, from the earliest to the latest.
Data Generator
Articulated Object Generation
Model
Paper
Venue
Website
GitHub
NAP
NAP: Neural 3D Articulated Object Prior
NeurIPS '23
-
CAGE
CAGE: Controllable Articulation Generation
CVPR '24
URDFormer
URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images
RSS '24
SINGAPO
SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects
ICLR '25
Real2Code
Real2code: Reconstruct Articulated Objects via Code Generation
ICLR '25
-
-
Articulate-Anything
Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
ICLR '25
MagicArticulate
MagicArticulate: Make Your 3D Models Articulation-Ready
CVPR '25
MeshArt
MeshArt: Generating Articulated Meshes with Structure-Guided Transformers
CVPR '25
PartRM
PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model
CVPR '25
-
ArtFormer
ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
CVPR '25
-
-
ArtiWorld
ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
arXiv '25
-
-
Articulate Anymesh
Articulate Anymesh: Open-Vocabulary 3D Articulated Objects Modeling
CoRL '25
-
ATOP
Articulate That Object Part (ATOP): 3D Part Articulation via Text and Motion Personalization
arXiv '25
-
-
URDF-Anything
URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
NeurIPS '25
ArtiLatent
ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
SIG. Asia '25
ArtGen
ArtGen: Conditional Generative Modeling of Articulated Objects in Arbitrary Part-Level States
arXiv '25
-
-
DreamArt
DreamArt: Generating Interactable Articulated Objects from a Single Image
arXiv '25
-
GAOT
GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models
ACM MM Asia '25
-
-
UniArt
UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation
arXiv '25
-
-
Infinite Mobility
Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation
arXiv '25
Kinematify
Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects
ICRA '26
-
Particulate
Particulate: Feed-Forward 3D Object Articulation
CVPR '26
-
URDF-Anything+
URDF-Anything+: Autoregressive Articulated 3D Models Generation for Physical Simulation
arXiv '26
ArtLLM
ArtLLM: Generating Articulated Assets via 3D LLM
CVPR '26
-
SPARK
SPARK: Sim-Ready Part-Level Articulated Reconstruction with VLM Knowledge
Stable dynamics and articulated control benchmarking
Isaac Sim
Robotics simulator
Photorealistic rendering and PhysX-based simulation
Habitat
Embodied AI platform
Large-scale navigation and interactive embodied environments
ManiSkill
Robotics benchmark and simulator
High-throughput embodied manipulation evaluation
OmniGibson
Embodied simulation platform
Rich object semantics and interactive scene modeling
AI2-THOR
Embodied AI simulator
Procedural indoor environments for navigation and interaction
Asset and Scene Formats
Format
Use Case
Notes
URDF
Robot and articulated asset description
Widely used for kinematic structures in robotics
MJCF
Physics-centric simulation description
Common in MuJoCo-based embodied benchmarks
USD
Scene and asset interchange
Increasingly used in modern simulation pipelines
glTF / GLB
3D asset exchange
Lightweight format for geometry and materials
OBJ
Mesh storage
Common geometry format but limited semantics
Evaluation
We recommend evaluating embodied 3D generation at three levels:
Geometric Fidelity: shape and appearance quality
Physical Plausibility and Simulation Compatibility: stability, articulation correctness, collision validity, material realism, and simulator readiness
Downstream Embodied Task Performance: grasp success, articulated manipulation success, navigation success, task completion, and sim-to-real transfer performance
Citation
If you find this repository useful, please consider citing our survey.
@article{to_be_updated,
title = {3D Generation for Embodied AI and Robotic Simulation: A Survey},
author = {To be updated},
journal = {To be updated},
year = {2025}
}