SceneMI: Motion In-betweening for Modeling Human-Scene Interactions

🛠️ Setup

# Create environment
conda create -n scenemi python=3.9
conda activate scenemi

# Install dependencies
pip install -r requirements.txt

📁 Dataset and Preparation

1. Download the TRUMANS dataset and place it under:

   dataset/TRUMANS/Data_release/
   

2. Download SMPL-X body models and place them under:

   body_models/smplx/
   

3. Preprocess the dataset:

   python preprocess_dataset.py

🚀 Training

To train the diffusion-based SceneMI model:

python -m train.train_diffusion_scenemib

⭐ Citation

@misc{hwang2025scenemimotioninbetweeningmodeling,
    title={SceneMI: Motion In-betweening for Modeling Human-Scene Interactions}, 
    author={Inwoo Hwang and Bing Zhou and Young Min Kim and Jian Wang and Chuan Guo},
    year={2025},
    eprint={2503.16289},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2503.16289}, 
}

🤝 Acknowledgements

We sincerely thank the open-source projects that our code builds upon and draws inspiration from:
CondMDI, TRUMANS and MDM.