Research map / Video / Video generation
ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer
Jiazhi Guan, Zhiliang Xu, Hang Zhou, Kaisiyuan Wang, Shengyi He, Zhanwang Zhang, Borong Liang, Haocheng Feng, Errui Ding, Jingtuo Liu, Jingdong Wang, Youjian Zhao and 1 more
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 3D mesh guidance into the generator's feature maps (ablation) | ReSyncer Ours-Sync · VoxCeleb2 | DeltaSync: 2.54 -> 0.88 | Improved |
| add 3D mesh guidance into the generator's feature maps (ablation) | ReSyncer Ours-Sync · VoxCeleb2 | LMD: 3.60 -> 3.19 | Improved |
| feed mesh content into the W-space vector (ablation) | ReSyncer Ours-Sync · VoxCeleb2 | DeltaSync: 1.02 -> 0.88 | Improved |
| increase speaking-style reference length from 50 to 90 frames (ablation) | Style-SyncFormer · VoxCeleb2 | DeltaSync: 0.95 -> 0.88 | Improved |
| extend style reference length from 90 to 200 frames (ablation) | Style-SyncFormer · VoxCeleb2 | DeltaSync: 0.88 -> 0.88 | No clear effect |
| use ReSyncer instead of StyleSync for generalized lip-sync | ReSyncer · VoxCeleb2 | DeltaSync: 1.57 -> 0.88 | Improved |
| use ReSyncer face swap versus StyleSwap | ReSyncer · FaceForensics++ | ID Retrieval (%): 97.05% -> 96.70% | Mixed |
| use FaceFormer-style one-hot speaker embedding instead of style-injected Style-SyncFormer (ablation) | 3D dynamics prediction · generalized lip-sync | LMD and DeltaSync | Improved |
| use Hifi3DFace topology instead of BFM (ablation) | ReSyncer · lip-sync | visual and sync quality | No clear effect |
| personalized fine-tuning versus StyleSync-P | ReSyncer · Personalized lip-sync | DeltaSync: 0.55 vs 0.55 | No clear effect |
Closest papers by meaning
- StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator (CVPR 2023 · similarity 0.94)
- OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers (NeurIPS 2025 · similarity 0.89)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.88)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025 · similarity 0.88)
- DiVAS: Video and Audio Synchronization with Dynamic Frame Rates (CVPR 2024 · similarity 0.88)
- SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis (CVPR 2024 · similarity 0.87)
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.
