Fudan-fMRI/MinD-3D-pp

MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset (TPAMI 2025)

Notes

• 🔥 We have released all the weights of MinD-3D++, trained on fMRI-Shape and fMRI-Objaverse.
• 🔥 We also provide a jointly trained model on Subject 1.
• 🔥 Subjects 1, 4, 6, 8 in fMRI-Shape and fMRI-Objaverse correspond to Subjects 3, 4, 1, 2 in CineBrain.

Citation

If you find our paper useful for your research and applications, please cite using this BibTeX:

@misc{gao2023mind3d,
      title={MinD-3D: Reconstruct High-quality 3D objects in Human Brain}, 
      author={Jianxiong Gao and Yuqian Fu and Yun Wang and Xuelin Qian and Jianfeng Feng and Yanwei Fu},
      year={2023},
      eprint={2312.07485},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{gao2025mind3dadvancingfmribased3d,
      title={MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset}, 
      author={Jianxiong Gao and Yanwei Fu and Yuqian Fu and Yun Wang and Xuelin Qian and Jianfeng Feng},
      year={2025},
      eprint={2409.11315},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2409.11315}, 
}

@misc{gao2025cinebrain,
      title={CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing}, 
      author={Jianxiong Gao and Yichang Liu and Baofeng Yang and Jianfeng Feng and Yanwei Fu},
      year={2025},
      eprint={2503.06940},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.06940}, 
}