AI Paper Atlas

Research map / Video / Video generation

CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing

Gaoxiang Cong, Liang Li, Jiaxin Ye, Zhedong Zhang, Hongming Shan, Yuankai Qi, Qingming Huang

ECCV 2026 · Video › Video generation · approach: Video-to-audio synthesis · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add acoustic style adapting phase (ablation)CoSync-DiT · CelebV-Dub Setting 2SPKSIM: 19.64 -> 53.44Improved
add fine-grained visual calibrating (ablation)CoSync-DiT · CelebV-Dub Setting 2Sync-KL: 0.419 -> 0.381Improved
add time-aware context aligning (ablation)CoSync-DiT · CelebV-Dub Setting 2Sync-KL: 0.446 -> 0.381Improved
add time-aware context aligning (ablation)CoSync-DiT · CelebV-Dub Setting 2WER: 7.39 -> 6.39Improved
add JSAR (ablation)CoSync-DiT · CelebV-Dub Setting 2WER: 8.72 -> 6.39Improved
add JSAR (ablation)CoSync-DiT · CelebV-Dub Setting 2Sync-KL: 0.431 -> 0.381Improved
add semantic consistency (CTC) constraint (ablation)CoSync-DiT · CelebV-Dub Setting 2WER: 8.39 -> 6.39Improved
add temporal consistency (contrastive) constraint (ablation)CoSync-DiT · CelebV-Dub Setting 2Sync-KL: 0.425 -> 0.381Improved
add visual calibrating (ablation)CoSync-DiT · CelebV-Dub Setting 2SPKSIM: 53.25 -> 53.44No clear effect
use CoSync-DiT instead of AlignDiTAlignDiT · CelebV-Dub Setting 1SPKSIM: 59.71 -> 65.21Improved
use CoSync-DiT instead of AlignDiTAlignDiT · CelebV-Dub Setting 1AVSync: 49.05 -> 65.94Improved
use CoSync-DiT instead of InstructDubInstructDub · CelebV-Dub Setting 2WER: 5.64 -> 6.39Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy