Metraipolis › archive › dc_e54c85b67ea8

Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance — arXiv:2610.12316

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12316
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:57.818Z
SHA-256 of the archived text
fb1c75a83d8e234c441d1f9f7d7504e315822d7ff48f987d24560c44601b4bda
Stable URL of this page
https://metraipolis.com/documento/dc_e54c85b67ea8

How to cite

Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance — arXiv:2610.12316 — arXiv (en), https://arxiv.org/abs/2610.12316 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e54c85b67ea8 (Metraipolis archive dc_e54c85b67ea8, sha256 fb1c75a83d8e234c441d1f9f7d7504e315822d7ff48f987d24560c44601b4bda)
BibTeX
@misc{dce54c85b67ea8,
  title = {Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance — arXiv:2610.12316},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12316},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e54c85b67ea8; sha256 fb1c75a83d8e234c441d1f9f7d7504e315822d7ff48f987d24560c44601b4bda},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12316. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent motion generative models have demonstrated strong capabilities in synthesizing physically plausible character motion, but often overlook established animation principles used by professional animators to ground and design their animation work. Understanding and incorporating these principles into motion generative pipelines is essential for producing motions that serve not only physically grounded applications but also the needs of the character animation community. This enables the creation of characters that not only move in physically plausible ways but also feel alive, expressive, and engaging. To close this gap, we focus on the Exaggeration principle of animation and investigate how it can be incorporated into modern motion generative pipelines to produce more expressive character motions. To this end, we introduce a framework that operates at two stages of existing motion generative pipelines. The first stage introduces exaggeration during training, where we perform supervised fine-tuning of pre-trained text-to-motion models on our curated exaggeration dataset. The second stage operates at inference time, where we: (i) introduce a mathematical formulation of exaggeration based on dynamic movement primitives (DMPs); and (ii) leverage this formulation as an exaggeration guidance signal to guide existing diffusion and flow-matching text-to-motion generation models toward exaggerated motion without additional training. Through qualitative and quantitative evaluations against three strong motion generation models, we show that our methods generate more exaggerated and expressive motions while preserving neutral reference motion intent and physical plausibility.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12316 — 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 2026-10-09T05:55:07.691Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).