Research map / 3D vision / Face and shape
Parametric Implicit Face Representation for Audio-Driven Facial Reenactment
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 |
|---|---|---|---|
| Increase sequence length from k=1 to k=100 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | LMD: 2.556 -> 1.477 | Helped |
| Increase sequence length from k=1 to k=100 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | AVConf: 4.201 -> 7.071 | Helped |
| Increase sequence length from k=10 to k=100 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | LMD: 2.273 -> 1.477 | Helped |
| Increase sequence length from k=10 to k=100 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | AVConf: 4.505 -> 7.071 | Helped |
| Increase sequence length from k=50 to k=100 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | LMD: 1.626 -> 1.477 | Helped |
| Increase sequence length from k=50 to k=100 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | AVConf: 6.873 -> 7.071 | Helped |
| Increase sequence length from k=100 to k=200 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | LMD: 1.477 -> 1.650 | Hurt |
| Increase sequence length from k=100 to k=200 (ablation) | PIR audio-to-expression encoder · Sequence-length ablation | AVConf: 7.071 -> 6.929 | Hurt |
Closest papers by meaning
- AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis (AAAI 2024 · similarity 0.88)
- 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 0.87)
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio (CVPR 2024 · similarity 0.87)
- Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation (AAAI 2024 · similarity 0.87)
- Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications (CVPR 2024 · similarity 0.86)
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.