OpenReal2Sim is a toolbox for real-to-sim reconstruction and robotic simulation.
It supports our multiple research projects, including PhysWorld and RoLA.
- Real-to-sim assets reconstruction from images and (generated) videos
- IsaacLab support for scenario import, camera setup, and rendering from the same input viewpoint
- Preliminary IsaacLab support for robotic trajectory generation by cross-embodiment transfer from videos
- Preliminary Maniskills support
- Preliminary Mujoco support
Clone this repository recursively:
git clone git@github.com:PointsCoder/OpenReal2Sim.git --recurse-submodules
Next, we need to set up the Python environment. We recommend using docker for managing dependencies.
Please refer to docker installation for launching the docker environment.
Please follow the step-by-step user guide here.
If you find this repository useful in your research, please consider citing:
@misc{openreal2sim,
title={OpenReal2Sim: A Toolbox for Real-to-Sim Reconstruction and Robotic Simulation},
author={OpenReal2Sim Development Team},
year={2025}
}
@inproceedings{physworld,
title={Robot Learning from a Physical World Model},
author = {Mao, Jiageng and He, Sicheng and Wu, Hao-Ning and You, Yang and Sun, Shuyang and Wang, Zhicheng and Bao, Yanan and Chen, Huizhong and Guibas, Leonidas and Guizilini, Vitor and Zhou, Howard and Wang, Yue},
year={2025},
}
@inproceedings{rola,
title={Robot learning from any images},
author={Zhao, Siheng and Mao, Jiageng and Chow, Wei and Shangguan, Zeyu and Shi, Tianheng and Xue, Rong and Zheng, Yuxi and Weng, Yijia and You, Yang and Seita, Daniel and others},
booktitle={Conference on Robot Learning},
pages={4226--4245},
year={2025},
organization={PMLR}
}