[Submitted on 2 Nov 2026]
Authors:Yexin Liu, Yunlong Lin, Zehan Wang, Guangxin He, Xinli Xu, Jiajun Zha, Yaofu Liu, Yueze Wang, Bowen Ping, Yuanming Li, Amie Wang, Bernard Ghanem, Bing Li, Harry Yang
Abstract:Video dubbing aims to synthesize lip movements that match target speech while preserving the speaker identity, head pose, and background of a source video. Existing editors are predominantly trained via self-reconstruction under original paired audio, even though the source mouth becomes a conflicting target when driving speech is replaced. We introduce replacement-aware cross-audio supervision: paired-audio samples use full-frame reconstruction, whereas unpaired replacement-audio samples mask out source-mouth reconstruction losses and supervise the mouth solely through audio-visual synchronization while preserving unmasked facial regions and background. Because offline dubbing provides the complete source video and target speech beforehand, we present VidDub, a full-context diffusion editor distilled into two denoising steps (2 NFE). Our replacement-aware teacher first learns accurate lip synchronization without regressing toward conflicting source mouth movements. Matched trajectory regression then transfers the teacher’s CFG-guided trajectories to a two-step student, and distribution matching distillation recovers visual quality after step compression. We will release the curated training dataset, VidDub-Bench, fixed paired- and cross-audio evaluation manifests, preprocessing outputs, and unified evaluation code. Across three training seeds, masking out conflicting source-mouth reconstruction improves cross-audio Sync-C by 0.833; the final two-step model combines strong lip synchronization with superior visual quality, identity preservation, and visual speech recognition across four benchmarks.
Submission history
From: Yexin Liu [view email]
[v1] Mon, 2 Nov 2026 16:33:09 UTC (24,580 KB)
