MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

Nhat M. Hoang^1,2*  Gong Kehong²⁺  Chuan Guo^2*  Michael Bi Mi² 

¹Nanyang Technological University  ²Huawei Technologies Co., Ltd 

^*Work done while interning at Huawei ⁺Corresponding author

This repository contains the official implementation of MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation.
Please refer to our project page for more visualizations.

Updates

[TBC] Release training and inference code for the model MDM (text-to-motion, action-to-motion).

[TBC] Release training and inference code for the model EDGE (music-to-dance).

[02/2024] Release training and inference code for the model MotionDiffuse (text-to-motion).

[01/2024] Paper uploaded to arXiv.

[12/2023] Paper accepted at AAAI-24 Main Track! 🎉

Citation

If you find our work useful for your research and development, please consider citing the paper:

@misc{hoang2024motionmix,
  title={MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation}, 
  author={Nhat M. Hoang and Kehong Gong and Chuan Guo and Michael Bi Mi},
  year={2024},
  eprint={2401.11115},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}