Research map / Video / Video generation
Neural Voice Puppetry: Audio-driven Facial Reenactment
Justus Thies, Mohamed Elgharib, Ayush Tewari, Christian Theobalt, Matthias Nießner
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 dilated instead of strided convolutions in rendering network (ablation) | rendering network · Obama self-reenactment (visual tracking) | PSNR: 40.12 -> 41.48 | Improved |
| use dilated instead of strided convolutions in rendering network (ablation) | rendering network · Obama self-reenactment (audio-based) | PSNR: 36.32 -> 36.65 | Improved |
| add temporal expression prediction network (ablation) | audio-expression estimation · Obama self-reenactment | relative 2D mouth landmark error: 0.058 -> 0.055 | Improved |
| train expression network on multiple targets instead of only Obama (ablation) | audio-expression network · multiple target videos | prediction coherence: 3145 -> 302750 frames | Improved |
| drive rendering with audio-based expressions instead of visual tracking | Neural Voice Puppetry · Obama self-reenactment | PSNR: 41.48 -> 36.65 | Hurt |
| drive rendering with audio-based expressions instead of visual tracking | Neural Voice Puppetry · Obama self-reenactment | relative 2D mouth landmark error: 0.022 -> 0.055 | Hurt |
| use generalized network instead of person-specific one trained on 14 hours | Neural Voice Puppetry · Obama lip sync | SyncNet confidence: 5.9 -> 5.2 | No clear effect |
Closest papers by meaning
- Realistic Speech-Driven Facial Animation with GANs (IJCV 2019 · similarity 0.90)
- Parametric Implicit Face Representation for Audio-Driven Facial Reenactment (CVPR 2023 · similarity 0.90)
- FaceFormer: Speech-Driven 3D Facial Animation With Transformers (CVPR 2022 · similarity 0.89)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.88)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.88)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.88)
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.
