Metraipolis › archive › dc_8eed8715b620
GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression — arXiv:2609.21576
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21576
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:44:15.685Z
- SHA-256 of the archived text
48a8881345334f64a51260dc98fb756b288595989be1ada9bea3b8567ce803a5- Stable URL of this page
https://metraipolis.com/documento/dc_8eed8715b620
How to cite
GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression — arXiv:2609.21576 — arXiv (en), https://arxiv.org/abs/2609.21576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8eed8715b620 (Metraipolis archive dc_8eed8715b620, sha256 48a8881345334f64a51260dc98fb756b288595989be1ada9bea3b8567ce803a5)
BibTeX
@misc{dc8eed8715b620,
title = {GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression — arXiv:2609.21576},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21576},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8eed8715b620; sha256 48a8881345334f64a51260dc98fb756b288595989be1ada9bea3b8567ce803a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generating natural co-speech gestures from streaming speech is essential for embodied conversational agents, where motion must be produced while a user is still speaking. Recent streaming gesture systems make online generation possible by autoregressing over discrete motion tokens, but this design compresses high-dimensional continuous motion into finite codebooks and can limit the realism and diversity of generated gestures. To preserve both causality and continuous expressiveness, we propose \textbf{GestureFAR}, a flow-autoregressive framework for streaming co-speech gesture generation. First, GestureFAR autoregresses over causal continuous motion latents, using a transformer to model streaming audio-motion context and a per-token flow-matching head to sample the next latent from a continuous distribution. Second, we introduce a head-only flow distillation strategy that freezes the causal backbone and distills the multi-step per-token flow head into a single network evaluation using consistency and distribution-matching objectives. This keeps the model token-causal while removing the main latency bottleneck for live interaction. Experiments on BEAT2 show that GestureFAR significantly improves the quality--latency trade-off among streaming-capable methods, preserving strong gesture quality while enabling real-time token-causal generation. Project Page: this https URL
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.HC).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.21576 — 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 2026-10-10T01:13:57.231Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).