GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Datas

Wentao Wang^1*  Hang Ye^1*  Fangzhou Hong³  Xue Yang¹  Jianfu Zhang⁴  Yizhou Wang²  Ziwei Liu³  Liang Pan^1† 

¹Shanghai AI Laboratory  ²Peking University  ³Nanyang Technological University  ³Shanghai Jiao Tong University 
^*Equal Contribution ^†Corresponding Author

GeneMAN is a generalizable framework for single-view-to-3D human reconstruction, built on a collection of multi-source human data. Given a single in-the-wild image of a person, GeneMAN could reconstruct a high-quality 3D human model, regardless of its clothing, pose, or body proportions (e.g., a full-body, a half-body, or a close-up shot) in the given image.

---

[Project Page] • [arXiv] • [Demo Video]

Citation

If you find this work useful for your research, please consider citing our paper:

@article{wang2024geneman,
  title={GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data},
  author={Wang, Wentao and Ye, Hang and Hong, Fangzhou and Yang, Xue and Zhang, Jianfu and Wang, Yizhou and Liu, Ziwei and Pan, Liang},
  journal={arXiv preprint arXiv:2411.18624},
  year={2024}
}