[Project Page] [arXiv]

• License
• Description
  • Setup
  • Training
  • Eval
• Citation
• Acknowledgments
• Contact

Software Copyright License for non-commercial scientific research purposes. Please read carefully the terms and conditions and any accompanying documentation before you download and/or use the SGNify model, data and software, (the "Model & Software"), including 3D meshes, blend weights, blend shapes, textures, software, scripts, and animations. By downloading and/or using the Model & Software (including downloading, cloning, installing, and any other use of this github repository), you acknowledge that you have read these terms and conditions, understand them, and agree to be bound by them. If you do not agree with these terms and conditions, you must not download and/or use the Model & Software. Any infringement of the terms of this agreement will automatically terminate your rights under this License.

This repository contains the training code used for the experiments in Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance.

1. Create an account at https://arteq.is.tue.mpg.de/
2. Run ./install.sh
3. Activate the environment conda activate arteq

Run the following command to execute the code:

python src/train.py \
    --EPN_input_radius 0.4 \
    --EPN_layer_num 2 \
    --aug_type so3 \
    --batch_size 2 \
    --epochs 15 \
    --gt_part_seg auto \
    --i 0 \
    --kinematic_cond yes \
    --num_point 5000

Run the following command to evaluate the model:

python src/eval.py \
    --EPN_input_radius 0.4 \
    --EPN_layer_num 2 \
    --aug_type so3 \
    --epoch 15 \
    --gt_part_seg auto \
    --i 0 \
    --kinematic_cond yes \
    --num_point 5000

or with --paper_model.

If you find this Model & Software useful in your research we would kindly ask you to cite:

@misc{feng2023generalizing,
      title={Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance},
      author={Haiwen Feng and Peter Kulits and Shichen Liu and Michael J. Black and Victoria Abrevaya},
      year={2023},
      eprint={2304.10528},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@TODO

For questions, please contact [email protected].

For commercial licensing (and all related questions for business applications), please contact [email protected].