Metraipolis › archive › dc_eb6bf02822f6
MotionMaestro: Masked Tokenization for Unified Motion Generation — arXiv:2609.37495
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37495
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:41:19.996Z
- SHA-256 of the archived text
db9d181cd22d18174628ad2c08066637f6fdb5552a418749303d98bea924e2ed- Stable URL of this page
https://metraipolis.com/documento/dc_eb6bf02822f6
How to cite
MotionMaestro: Masked Tokenization for Unified Motion Generation — arXiv:2609.37495 — arXiv (en), https://arxiv.org/abs/2609.37495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb6bf02822f6 (Metraipolis archive dc_eb6bf02822f6, sha256 db9d181cd22d18174628ad2c08066637f6fdb5552a418749303d98bea924e2ed)
BibTeX
@misc{dceb6bf02822f6,
title = {MotionMaestro: Masked Tokenization for Unified Motion Generation — arXiv:2609.37495},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37495},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb6bf02822f6; sha256 db9d181cd22d18174628ad2c08066637f6fdb5552a418749303d98bea924e2ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human motion generation plays an important role in applications such as character animation, virtual environments, and embodied interaction. While existing approaches have achieved remarkable progress, many of them are developed for individual tasks, including text-to-motion, pose-conditioned generation, and trajectory control. Although these tasks involve different types of conditions, a unified framework capable of handling them within a common representation would greatly simplify motion generation systems. We observe that diverse motion conditions can be naturally formulated as different observation patterns over motion sequences, where each task corresponds to a specific masking strategy. Based on this insight, we introduce MotionMaestro, a unified motion generation framework that learns a shared representation for complete motions and heterogeneous partial observations through masked motion tokenization. MotionMaestro employs a three-stage training strategy that first learns a masked motion tokenizer, then refines its reconstruction ability on clean motions, and finally trains a conditional flow-matching generator in the learned latent space. Furthermore, we introduce an observation map and an observation loss to explicitly preserve provided motion conditions during generation. With this unified representation and conditioning mechanism, MotionMaestro supports text-guided and unconditional synthesis, pose conditioning and partial completion, temporal interpolation, trajectory control, and motion continuation. Experiments on the large-scale RoMo and MotionMillion datasets show state-of-the-art performance across diverse motion generation tasks. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.37495 — 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 2026-10-07T18:04:24.879Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).