Research map / 3D vision / NeRF and radiance fields
AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis
Yudong Guo, Keyu Chen, Sen Liang, Yong-Jin Liu, Hujun Bao, Juyong Zhang
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 |
|---|---|---|---|
| condition NeRF directly on audio features instead of intermediate expression (ablation) | AD-NeRF · Test sequence (500 frames) | SSIM: 0.88 -> 0.92 | Improved |
| train separate NeRFs for head and torso instead of one NeRF (ablation) | AD-NeRF · Test sequence (500 frames) | SSIM: 0.87 -> 0.92 | Improved |
| direct audio condition vs audio-estimated expression code (ablation) | AD-NeRF · qualitative lip sync | lip synchronization | Improved |
| separate head and torso NeRFs (ablation) | AD-NeRF · qualitative boundary error | photometric error | Improved |
| compare AD-NeRF with Chen et al. | AD-NeRF · Testset A | SyncNet confidence: 6.129 vs 5.239 | Hurt |
| compare AD-NeRF with Vougioukas et al. | AD-NeRF · Testset B | SyncNet confidence: 6.712 vs 5.411 | Hurt |
| compare AD-NeRF with Chen et al. on AU error | AD-NeRF · Testset B | AU error: 3.475 -> 2.287 | Improved |
| compare AD-NeRF with Wiles et al. on AU error | AD-NeRF · Testset A | AU error: 3.134 -> 2.133 | Improved |
Closest papers by meaning
- AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis (AAAI 2024 · similarity 0.93)
- Hierarchically Controlled Deformable 3D Gaussians for Talking Head Synthesis (AAAI 2025 · similarity 0.89)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.89)
- SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis (CVPR 2024 · similarity 0.88)
- PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis (AAAI 2025 · similarity 0.87)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 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.
