Metraipolis › archive › dc_7c23a35774da

MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation — arXiv:2609.14965

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14965
License (as archived)
CC0-1.0
Archived
2026-10-16T01:53:20.009Z
SHA-256 of the archived text
f9e51fe837ae9e1c323a9233eb56abff8e9335f5a2746aa9ff8738ed7d69698a
Stable URL of this page
https://metraipolis.com/documento/dc_7c23a35774da

How to cite

MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation — arXiv:2609.14965 — arXiv (en), https://arxiv.org/abs/2609.14965 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c23a35774da (Metraipolis archive dc_7c23a35774da, sha256 f9e51fe837ae9e1c323a9233eb56abff8e9335f5a2746aa9ff8738ed7d69698a)
BibTeX
@misc{dc7c23a35774da,
  title = {MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation — arXiv:2609.14965},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14965},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c23a35774da; sha256 f9e51fe837ae9e1c323a9233eb56abff8e9335f5a2746aa9ff8738ed7d69698a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14965. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-driven 3D human motion generation models face significant challenges in responding to diverse and unconstrained textual prompts, primarily due to the limited availability of 3D motion training data. To address this, we introduce MoVT, a novel framework that effectively leverages the extensive range of human action videos to enhance text-to-motion generation. At the core of our approach is the cross-modal augmented motion tokenizer, which projects discrete 3D motion tokens into the 2D domain. This projection allows us to enrich the motion codebook with complex, real-world motion patterns derived from videos. The enriched discrete tokens are then mapped back to the 3D domain, resulting in aligned 3D and 2D codebooks with an enhanced capacity to represent intricate motions. These enhanced codebooks are integrated into a generative masked transformer, which predicts masked motion token indices in a modality-agnostic manner. This enables the use of text-index pairs, generated from the 2D codebook and annotated motion videos, to further enhance the generator. Extensive empirical evaluations show that MoVT performs favorably against prior state-of-the-art methods across multiple key metrics.

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/2609.14965 — 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 2026-10-16T01:25:23.628Z 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).