Research map / Video / Video generation
Realistic Speech-Driven Facial Animation with GANs
Konstantinos Vougioukas, Stavros Petridis, Maja Pantić
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 sequence discriminator (ablation) | Proposed Model · GRID | blinks/sec: 0.03 -> 0.45 | Improved |
| add sync discriminator (ablation) | Proposed Model · GRID | WER: 27.8% -> 23.1% | Improved |
| add frame discriminator (ablation) | Proposed Model · GRID | CPBD sharpness: 0.252 -> 0.268 | Improved |
| add frame discriminator (ablation) | Proposed Model · GRID | blinks/sec: 0.16 -> 0.45 | Improved |
| add L1 reconstruction loss on lower face (ablation) | Proposed Model · GRID | WER: 56.4% -> 23.1% | Improved |
| add adversarial losses (ablation) | Proposed Model · GRID | WER: 26.6% -> 23.1% | Improved |
| add adversarial losses (ablation) | Proposed Model · GRID | PSNR: 28.467 -> 27.100 | Hurt |
| add sequence discriminator (ablation) | Proposed Model · GRID | PSNR: 27.590 -> 27.100 | Hurt |
| add sequence discriminator (ablation) | Proposed Model · GRID | WER: 27.0% -> 23.1% | Improved |
| add frame discriminator (ablation) | Proposed Model · GRID | ACD: 1.96 -> 1.47 | Improved |
| use temporal generator with sync discriminator instead of static baseline | Proposed Model · GRID | WER: 36.4% -> 23.1% | Improved |
| use temporal generator instead of static baseline | Proposed Model · TCD TIMIT | AV confidence: 1.4 -> 5.5 | Improved |
Closest papers by meaning
- FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning (ICCV 2021 · similarity 0.93)
- SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis (CVPR 2024 · similarity 0.90)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.90)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.90)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.89)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.89)
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.
