zju3dv / closemocap

Official implementation of "Reconstructing Close Human Interaction from Multiple Views"

CloseMoCap

---

demo_558_concat.mp4

demo_556_concat_fps60.mp4

demo_511.mp4

This repository holds the code for our SIGGRAPH Asia 2023 project "Reconstructing Close Human Interaction from Multiple Views". The paper focuses on human pose estimation in close interaction scenarios. The code and data will be made publicly available soon, please stay tuned.

Citation

If you find this code useful for your research, please cite us using the following BibTeX entry.

@article{shuai2023CloseMoCap,
  title = {Reconstructing Close Human Interactions from Multiple Views},
  author = {Shuai, Qing and Yu, Zhiyuan and Zhou, Zhize and Fan, Lixin and Yang, Haijun and Yang, Can and Zhou, Xiaowei},
  year = {2023},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3618336},
  journal = {ACM Transactions on Graphics},
  month = {dec},
  numpages = {14}
}

closemocap's Issues

Code release

Fantastic work and great paper, thanks!
do you have a timeline for releasing the code and trained weights? I am interested in leveraging these detailed results in sports scientific research.

Thanks!
Tobi