Metraipolis › archive › dc_d208edc55e50

TalkFlow: Structured Latent Flow Matching for Speech Driven Holistic Motion Generation — arXiv:2610.40972

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40972
License (as archived)
CC0-1.0
Archived
2026-11-02T08:03:38.082Z
SHA-256 of the archived text
bf2ddc5be130bb36b289eb47bf600d216abdb0debc1b01b16011d80311957f9a
Stable URL of this page
https://metraipolis.com/documento/dc_d208edc55e50

How to cite

TalkFlow: Structured Latent Flow Matching for Speech Driven Holistic Motion Generation — arXiv:2610.40972 — arXiv (en), https://arxiv.org/abs/2610.40972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d208edc55e50 (Metraipolis archive dc_d208edc55e50, sha256 bf2ddc5be130bb36b289eb47bf600d216abdb0debc1b01b16011d80311957f9a)
BibTeX
@misc{dcd208edc55e50,
  title = {TalkFlow: Structured Latent Flow Matching for Speech Driven Holistic Motion Generation — arXiv:2610.40972},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40972},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d208edc55e50; sha256 bf2ddc5be130bb36b289eb47bf600d216abdb0debc1b01b16011d80311957f9a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Holistic co-speech motion generation aims to synthesize coordinated facial expressions, hand gestures, and body movements from speech, which is challenging due to heterogeneous part-specific dynamics, long-range temporal coherence, and cross-part coordination. Directly modeling high-dimensional motion can be unstable, while overly compact or unstructured latent spaces may lose fine-grained motion details. We present \textbf{TalkFlow}, a structured latent flow framework for speech-driven holistic motion generation. TalkFlow learns a continuous three-stream latent representation for upper-body motion, lower-body motion, and facial expressions, preserving part-specific dynamics without forcing heterogeneous motion components into a single latent space. To maintain holistic coordination, lightweight cross-stream interactions are incorporated in both latent representation learning and flow-based generation. Conditioned on multi-level speech features, TalkFlow performs speech-conditioned latent flow matching, learning a continuous transport process from source latents to realistic motion latents. Experiments on the BEAT2 dataset demonstrate strong performance across facial expression accuracy, body gesture quality, and speech-motion synchronization. Qualitative comparisons and user studies further show that TalkFlow generates more natural, expressive, and speech-aligned holistic motion than state-of-the-art methods. The project page is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.40972 — 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 2026-11-02T07:44:00.783Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).