Research map / Video / Video generation
StyleLipSync: Style-based Personalized Lip-sync Video Generation
Taekyung Ki, Dongchan Min
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 |
|---|---|---|---|
| use pose-aware masking from a 3D facial mesh instead of rectangular masking (ablation) | StyleLipSync · Voxceleb2 reconstruction | PSNR: 18.867 -> 19.607 | Improved |
| add moving-average latent smoothing (MaLS) (ablation) | StyleLipSync · Voxceleb2 reconstruction | LSE-D: 6.994 -> 6.628 | Improved |
| use modulated convolution in style-aware masked fusion (SaMF) (ablation) | StyleLipSync · Voxceleb2 reconstruction | PSNR: 18.181 -> 19.607 | Improved |
| fine-tune decoder on target video without the sync regularizer (ablation) | StyleLipSync adaptation · unseen-face adaptation | lip-sync metrics | Hurt |
| add sync regularizer with sync loss using training-set audio (ablation) | StyleLipSync adaptation · unseen-face adaptation | lip-sync metrics | Improved |
| use sync regularizer without the sync loss (ablation) | StyleLipSync adaptation · unseen-face adaptation | lip-sync metrics | Mixed |
| personalize decoder to target video versus zero-shot | StyleLipSync · HDTF user study MOS | face similarity / lip-sync accuracy: face similarity 3.42 -> 4.03; lip-sync 4.01 -> 3.52 | Mixed |
| StyleLipSync versus Wav2Lip on LSE-C | StyleLipSync · Voxceleb2 reconstruction | LSE-C: 8.329 -> 8.056 | Hurt |
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)
- Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes (NeurIPS 2024 · similarity 0.87)
- DiVAS: Video and Audio Synchronization with Dynamic Frame Rates (CVPR 2024 · similarity 0.86)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025 · similarity 0.85)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.85)
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.
