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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add acoustic style adapting phase (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | SPKSIM: 19.64 -> 53.44 | Improved |
| add fine-grained visual calibrating (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | Sync-KL: 0.419 -> 0.381 | Improved |
| add time-aware context aligning (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | Sync-KL: 0.446 -> 0.381 | Improved |
| add time-aware context aligning (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | WER: 7.39 -> 6.39 | Improved |
| add JSAR (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | WER: 8.72 -> 6.39 | Improved |
| add JSAR (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | Sync-KL: 0.431 -> 0.381 | Improved |
| add semantic consistency (CTC) constraint (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | WER: 8.39 -> 6.39 | Improved |
| add temporal consistency (contrastive) constraint (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | Sync-KL: 0.425 -> 0.381 | Improved |
| add visual calibrating (ablation) | CoSync-DiT · CelebV-Dub Setting 2 | SPKSIM: 53.25 -> 53.44 | No clear effect |
| use CoSync-DiT instead of AlignDiT | AlignDiT · CelebV-Dub Setting 1 | SPKSIM: 59.71 -> 65.21 | Improved |
| use CoSync-DiT instead of AlignDiT | AlignDiT · CelebV-Dub Setting 1 | AVSync: 49.05 -> 65.94 | Improved |
| use CoSync-DiT instead of InstructDub | InstructDub · CelebV-Dub Setting 2 | WER: 5.64 -> 6.39 | Hurt |
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.
- EmoDubber — EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing (CVPR 2025) · better on 2 of 2 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
- Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners (CVPR 2024 · similarity 0.88)
- DiVAS: Video and Audio Synchronization with Dynamic Frame Rates (CVPR 2024 · similarity 0.88)
- Native Audio-Visual Alignment for Generation (NeurIPS 2026 · similarity 0.88)
- EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing (CVPR 2025 · similarity 0.87)
- OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers (NeurIPS 2025 · similarity 0.86)
- Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing (CVPR 2025 · similarity 0.86)
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.
