🌌 π³: Permutation-Equivariant Visual Geometry Learning

Yifan Wang¹, Jianjun Zhou¹²³, Haoyi Zhu¹, Wenzheng Chang¹, Yang Zhou¹,
Zizun Li¹, Junyi Chen¹, Jiangmiao Pang¹, Chunhua Shen², Tong He¹³†

¹ Shanghai AI Lab ² ZJU ³ SII
Equal Contribution † Corresponding Author

Note: This is updated version of the model.

@article{wang2025pi,
  title={$$\backslash$pi\^{} 3$: Permutation-Equivariant Visual Geometry Learning},
  author={Wang, Yifan and Zhou, Jianjun and Zhu, Haoyi and Chang, Wenzheng and Zhou, Yang and Li, Zizun and Chen, Junyi and Pang, Jiangmiao and Shen, Chunhua and He, Tong},
  journal={arXiv preprint arXiv:2507.13347},
  year={2025}
}