Metraipolis › archive › dc_80dceb31fab9

STyMo: Fast and Controllable Few-Shot Motion Style Transfer — arXiv:2609.04500

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04500
License (as archived): CC0-1.0
Archived: 2026-10-16T23:44:18.480Z
SHA-256 of the archived text: 98941c8e48f0fa134123570b21b20d73a8589c0e274aee348bcc8bbad6e4bcab
Stable URL of this page: https://metraipolis.com/documento/dc_80dceb31fab9

How to cite

STyMo: Fast and Controllable Few-Shot Motion Style Transfer — arXiv:2609.04500 — arXiv (en), https://arxiv.org/abs/2609.04500 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_80dceb31fab9 (Metraipolis archive dc_80dceb31fab9, sha256 98941c8e48f0fa134123570b21b20d73a8589c0e274aee348bcc8bbad6e4bcab)

BibTeX

@misc{dc80dceb31fab9,
  title = {STyMo: Fast and Controllable Few-Shot Motion Style Transfer — arXiv:2609.04500},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04500},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_80dceb31fab9; sha256 98941c8e48f0fa134123570b21b20d73a8589c0e274aee348bcc8bbad6e4bcab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04500. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Supporting a wide variety of motion styles is critical for creating diverse virtual characters, but current methods either require large stylized datasets or pre-trained models that cannot generalize beyond their training distribution. We present STyMo, a few-shot approach that learns motion style from only seconds of paired data and trains in one to two minutes. Our key insight is to decompose style into two components: a static component capturing time-invariant posture, and a temporal component capturing frame-wise dynamics. This decomposition yields an interpretable system where posture intensity, temporal exaggeration, and per-body-region style can be adjusted at runtime. Furthermore, the reduction in required training data and computation time structurally permits an iterative authoring workflow. To ensure robustness on arbitrary inputs, we further introduce a stylizability gate that automatically prevents artifacts on out-of-distribution motions. We demonstrate results across diverse motion styles, from subtle emotional variations to exaggerated character archetypes, and release our processed paired dataset to facilitate future research.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04500 — 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 2026-10-16T23:16:11.485Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).