SATA: Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation

Official repository for Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation.

SATA is a semantic-aware, topology-agnostic motion representation framework for heterogeneous character animation. It learns a unified latent motion manifold across diverse skeletal topologies and supports motion reconstruction, text-to-motion generation, and zero-shot cross-species retargeting.

We are actively working on releasing the code. Stay tuned :)

Links

• Project page
• Paper

Current Status

This repository is being prepared for public release. The code is currently under cleanup, and the first release will include the core implementation, usage instructions, and demo scripts.

TODO

• Release SATA encoder-decoder inference code.
• Add demos for encoding/decoding and retargeting.
• Add the data processing pipeline.
• Release SATA encoder-decoder training code.
• Add a text-to-motion demo with diverse skeletons.

Citation

@inproceedings{zhang2026sata,
  title     = {Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation},
  author    = {Zongye Zhang and Yuzhuo Cui and Qingjie Liu and Yunhong Wang},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  year      = {2026},
  note      = {To appear. arXiv:2605.27055},
  url       = {https://arxiv.org/abs/2605.27055}, 
}

Contact

For questions about the project, please contact the authors or open an issue after the initial code release.