Kinematic Frequency Motion — Released Weights
Learning Kinematic Frequency-Aware Disentanglement for Motion Style Transfer and Editing, SIGGRAPH Asia 2026.
These are the five checkpoints used by the paper figures and the live demo. The content motion is encoded by the motion VAE. The style motion is split by the IMF extractor into high-, mid-, and low-frequency bands. High and mid bands supply the fine style. A summary of the low band is encoded by MotionCLIP into the coarse-style token. The dual-style denoiser writes a latent, and the VAE decoder turns it back into a motion.
Files
Use the five files together. About 2.3 GB in total.
| File | Size | What it is |
|---|---|---|
motion_vae.ckpt |
929 MB | Motion VAE. It encodes the content motion and decodes the result. |
imf_extractor.pt |
91 MB | Three-band IMF extractor paired with the released denoiser. |
contact_timing.pt |
1.0 MB | Content-side contact-timing predictor. |
motionclip_checkpoint/motionclip.pth.tar |
217 MB | Trained MotionCLIP from MCM-LDM. It supplies the coarse-style token. |
dual_style_denoiser.ckpt |
1.03 GB | Dual-style denoiser paired with the released IMF extractor. |
SHA256SUMS lists the SHA-256 and byte size of each file. CLIP ViT-B/32 is not in this repository. The clip package downloads it on the first run.
Usage
hf download randong/kinematic-frequency-motion-weights --local-dir checkpoints
The Colab notebook and the live demo load these files with huggingface_hub. A local checkout can point checkpoints/ at the downloaded directory. Inference reads raw HumanML-263 features, shape [T, 263], at 20 Hz, and leaves them unnormalized.
Paper settings for the shipped clips: turning walk with a periodic dance kick uses coarse scale 2.5 and fine scale 1.5 (fine 10 for the dance accent). Stair walk with an energetic style uses coarse 2.5 and fine 3.
Citation
@inproceedings{dong2026kinematic,
title={Learning Kinematic Frequency-Aware Disentanglement for Motion Style Transfer and Editing},
author={Dong, Ran and Xie, Haoran and Yang, Xi},
booktitle={SIGGRAPH Asia 2026 Conference Papers},
year={2026},
note={to appear}
}