Research map / Image generation / Editing and style transfer
StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use StyleSync generalized generation instead of Wav2Lip-H | Lip-sync generation · LRW | SSIM: 0.80 -> 0.85 | Helped |
| Use StyleSync generalized generation instead of Wav2Lip-H | Lip-sync generation · VoxCeleb2 | LMD: 1.87 -> 1.47 | Helped |
| Apply personalized optimization to Ours-G | StyleSync · LRW | SSIM: 0.85 -> 0.88 | Helped |
| Apply personalized optimization to Ours-G | StyleSync · LRW | Sync_conf: 7.25 -> 6.35 | Hurt |
| Apply personalized optimization to Ours-G | StyleSync · VoxCeleb2 | LMD: 1.47 -> 1.15 | Helped |
| Apply personalized optimization to Ours-G | StyleSync · VoxCeleb2 | Sync_conf: 8.25 -> 7.26 | Hurt |
| Add low-level feature masking to face features (ablation) | StyleSync generalized model · VoxCeleb2 | LMD: 1.80 -> 1.47 | Helped |
| Add low-level feature masking to face features (ablation) | StyleSync generalized model · VoxCeleb2 | Sync_conf: 7.89 -> 8.25 | Helped |
| Add lip-sync loss during training (ablation) | StyleSync generalized model · VoxCeleb2 | LMD: 1.55 -> 1.47 | Helped |
| Add lip-sync loss during training (ablation) | StyleSync generalized model · VoxCeleb2 | Sync_conf: 7.41 -> 8.25 | Helped |
| Learn ΔW during personalized optimization (ablation) | StyleSync personalized model · VoxCeleb2 | D_ID: 0.92 -> 0.93 | Helped |
| Learn ΔW during personalized optimization (ablation) | StyleSync personalized model · VoxCeleb2 | SSIM: 0.82 -> 0.82 | No clear effect |
Closest papers by meaning
- OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers (NeurIPS 2025 · similarity 0.91)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025 · similarity 0.89)
- PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis (AAAI 2025 · similarity 0.88)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.88)
- DiVAS: Video and Audio Synchronization with Dynamic Frame Rates (CVPR 2024 · similarity 0.88)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · 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.