Metraipolis › archive › dc_24b2834bebda
UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance — arXiv:2610.05932
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05932
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:16.964Z
- SHA-256 of the archived text
208f9cae87410ecb02e5840bd6475c5bdda5a497296f24806eb646528ed6aa52- Stable URL of this page
https://metraipolis.com/documento/dc_24b2834bebda
How to cite
UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance — arXiv:2610.05932 — arXiv, https://arxiv.org/abs/2610.05932 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24b2834bebda (Metraipolis archive dc_24b2834bebda, sha256 208f9cae87410ecb02e5840bd6475c5bdda5a497296f24806eb646528ed6aa52)
BibTeX
@misc{dc24b2834bebda,
title = {UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance — arXiv:2610.05932},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05932},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24b2834bebda; sha256 208f9cae87410ecb02e5840bd6475c5bdda5a497296f24806eb646528ed6aa52},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05932. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual voice cloning requires intelligible, speaker-consistent speech synchronized with visible articulation. However, sequential multimodal conditioning can disrupt previously established temporal and speaker cues, while imbalanced inference guidance can improve linguistic accuracy at the expense of lip synchronization. In this paper, we propose UltraDub, a Unifying Visually-Steered Flow learning and trajectory Guidance Dubbing framework that leverages vision in two ways: as continuous motion for multimodal context aggregation, and as structural rhythm for trajectory rectification. Specifically, we introduce the Motion-guided Dual-context Retrieving (MDR) module, which continually recalibrates linguistic and speaker-style retrieval through shared lip-motion query residuals, utilizing independent time-conditioned gates to regulate their contributions. Furthermore, we propose Rhythm-anchored Trajectory Guidance (RTG), a training-free mechanism that evaluates hierarchical multimodal corrections at a visual-only predictive midpoint, safely strengthening semantic conditioning while better preserving temporal alignment. Finally, we construct DiverseDub, a multi-scenario benchmark to evaluate video dubbing in the wild. Extensive experiments demonstrate that UltraDub achieves state-of-the-art performance across four datasets. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Multimedia (cs.MM); Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.05932 — 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 2026-10-06T05:24:06.090Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).