zju3dv / TotalSelfScan

Code for "TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies" (NeurIPS 2022)

TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies

Project Page | Video | Paper | Data

TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies
Junting Dong*, Qi Fang*, Yudong Guo, Sida Peng, Qing Shuai, Hujun Bao, Xiaowei Zhou
NeurIPS 2022

training and animation

Please refer to the file train_pipeline.sh, where we describe the training and animation pipeline for one example subject.

Dataset

The dataset can be available here

cd xxx/TotalSelfScan
mkdir data
cd data
mkdir zju_snapshot
mv xxx/male-djt415_tshirt-smplh ./ 

Citation

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

@inproceedings{dong2022totalselfscan,
  title={TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies},
  author={Dong, Junting and Fang, Qi and Guo, Yudong and Peng, Sida and Shuai, Qing and Zhou, Xiaowei and Bao, Hujun},
  booktitle={Advances in Neural Information Processing Systems},
  year={2022}
}