Metraipolis › archive › dc_71568fe23249

PVSync: A Unified Lip-Sync Expert for Timing and Articulation — arXiv:2610.09223

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09223
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:01.680Z
SHA-256 of the archived text
bfeabe4fe93e624dc349db8decda01b689f61bb965b288bf6d7cc034cb82aa1e
Stable URL of this page
https://metraipolis.com/documento/dc_71568fe23249

How to cite

PVSync: A Unified Lip-Sync Expert for Timing and Articulation — arXiv:2610.09223 — arXiv (en), https://arxiv.org/abs/2610.09223 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71568fe23249 (Metraipolis archive dc_71568fe23249, sha256 bfeabe4fe93e624dc349db8decda01b689f61bb965b288bf6d7cc034cb82aa1e)
BibTeX
@misc{dc71568fe23249,
  title = {PVSync: A Unified Lip-Sync Expert for Timing and Articulation — arXiv:2610.09223},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09223},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71568fe23249; sha256 bfeabe4fe93e624dc349db8decda01b689f61bb965b288bf6d7cc034cb82aa1e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09223. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Lip movements can match the timing of speech without matching the spoken sounds. We introduce PVSync, a unified model for audio-visual offset estimation and phoneme-level articulation scoring. PVSync combines window-level contrastive learning for synchronisation with a phoneme-level articulation objective that aligns audio and video embeddings of the same viseme class across clips. Visemes group phonemes with similar visible articulation. Viseme labels are derived automatically from forced-aligned transcripts, without manual annotations. On offset-corrected videos from 13 talking-head video generation models, PVSync matches human rankings of lip-sync quality more closely than LSE-C, achieving a Spearman correlation of 0.83 versus 0.34. On an automatically constructed benchmark from held-out speech, PVSync distinguishes viseme-matched from mismatched audio-visual pairs with an ROC AUC of 0.91. PVSync also outperforms SyncNet and MTD-VocaLiST in temporal offset recovery on held-out in-the-wild clips. Code and benchmark data will be released upon acceptance.

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/2610.09223 — 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 2026-10-08T12:18:15.320Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).