Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI [CVPR'26 Highlight]

June 30, 2026 ยท View on GitHub

arXiv Website HF Dataset: Wanderland

Note

Downloaded data is selected through the public Hugging Face manifest. See download/ for quality-tier downloads such as showcase, evaluation_ready, and training_ready.

Release TODO

  • Simulation Code Release
  • [Jan 2026] 3D Reconstruction Benchmark Release
  • [Jan 2026] Data Release

Getting Started

Wanderland is a comprehensive framework that consists of many different components. Each component is relatively independent so please refer to the README.md file in each subfolder for more details. Note that all components use uv for dependency management. Please install uv first if you haven't done so.

curl -LsSf https://astral.sh/uv/install.sh | sh

Each component have its own virtual environment. Remember to deactivate and reactivate the venv when switching between different components.

Citation

@inproceedings{liu2026wanderland,
  title={Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI},
  author={Liu, Xinhao and Li, Jiaqi and Deng, Youming and Chen, Ruxin and Zhang, Yingjia and Ma, Yifei and Guo, Li and Li, Yiming and Zhang, Jing and Feng, Chen},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={1041--1052},
  year={2026}
}

Related Projects

Real-to-Sim:

3D Reconstruction:

Navigation:

Star History Chart