Metraipolis › archive › dc_43f244f0f46d

MorphoStyle: Motion Style Transfer with Morphology Control — arXiv:2609.14189

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14189
License (as archived)
CC0-1.0
Archived
2026-10-16T01:52:54.049Z
SHA-256 of the archived text
0c1800a220a4e08ee31cffa9d6a2ec2d7aebe66821c5f19e33c7b6e591ed30bf
Stable URL of this page
https://metraipolis.com/documento/dc_43f244f0f46d

How to cite

MorphoStyle: Motion Style Transfer with Morphology Control — arXiv:2609.14189 — arXiv (en), https://arxiv.org/abs/2609.14189 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43f244f0f46d (Metraipolis archive dc_43f244f0f46d, sha256 0c1800a220a4e08ee31cffa9d6a2ec2d7aebe66821c5f19e33c7b6e591ed30bf)
BibTeX
@misc{dc43f244f0f46d,
  title = {MorphoStyle: Motion Style Transfer with Morphology Control — arXiv:2609.14189},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14189},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43f244f0f46d; sha256 0c1800a220a4e08ee31cffa9d6a2ec2d7aebe66821c5f19e33c7b6e591ed30bf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14189. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human motion may be viewed as a combination of action content, style, and body morphology. Existing motion style transfer methods transfer a reference style onto a content motion while assuming a canonical body, whereas shape-aware motion generators adapt motion to a target shape without explicit style control. This separation of motion style and shape (morphology) makes it difficult to generate stylized motions for non-canonical bodies; naively combining a style transfer module with a shape-aware generator often leaks action content from the style reference and disrupts shape-consistent kinematics. We present MorphoStyle, a framework for shape-aware motion style transfer that is built on a shape-conditioned Finite-Scalar-Quantization Variational Auto-Encoder (FSQ-VAE). The key contribution is to pose the desired style transfer as modular latent disentanglement comprising: (i) a contrastive style encoder that extracts content-decoupled style embeddings; (ii) a text-guided style-routing mechanism that locates style-relevant joints in a text-motion feature space; and (iii) a manifold preserving style modulator that injects discriminative style embeddings in content features as a temporally-gated low-rank offset. Extensive experiments on benchmark datasets demonstrate that MorphoStyle outperforms competing baselines in terms of both shape control and motion style transfer, while simultaneously providing quantitative shape control. For more details, please see project website: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.14189 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T01:25:23.560Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).