Metraipolis › archive › dc_938cfac236bd
No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping — arXiv:2610.11070
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11070
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:16.752Z
- SHA-256 of the archived text
b703749cb236fb08c72303c089daa2fcab9436ff7d8c85c96b9b887dd4eefdeb- Stable URL of this page
https://metraipolis.com/documento/dc_938cfac236bd
How to cite
No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping — arXiv:2610.11070 — arXiv (en), https://arxiv.org/abs/2610.11070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_938cfac236bd (Metraipolis archive dc_938cfac236bd, sha256 b703749cb236fb08c72303c089daa2fcab9436ff7d8c85c96b9b887dd4eefdeb)
BibTeX
@misc{dc938cfac236bd,
title = {No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping — arXiv:2610.11070},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11070},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_938cfac236bd; sha256 b703749cb236fb08c72303c089daa2fcab9436ff7d8c85c96b9b887dd4eefdeb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio-driven facial animation underpins real-time avatars, telepresence, and embodied virtual agents. And it must run online: each frame emitted from audio observed up to the current time, at interactive rates. Recent progress is dominated by diffusion models, which need many network evaluations per sample and are therefore a poor fit for streaming. We argue the cost is unnecessary in this domain. Audio-conditioned facial motion occupies a comparatively low-dimensional manifold, a regime where a single-pass GAN suffices. The obstacle is not capacity but stochastic structure. We show that a causal, time-invariant generator driven by i.i.d. noise cannot suppress its output spectrum over a band without collapsing its per-step innovation. We proposed FaceGAN, which dissolved the limitation by shaping the noise pathway acausally. Because the driving noise is synthetic, its future can be sampled now, so the audio-to-expression path stays causal, and the model supports fully causal operation. FaceGAN emits expression and head pose in a single forward pass per frame and matches or outperforms state-of-art approaches in generation quality. Being feed-forward with bounded attention windows, it generates indefinitely without drift. 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/2610.11070 — 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 2026-10-09T05:55:07.096Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).