Research map / Video / Video generation
S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis
Dongze Li, Kang Zhao, Wei Wang, Yifeng Ma, Bo Peng, Yingya Zhang, Jing Dong
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 |
|---|---|---|---|
| replace the naive deformation module with the cross-modal facial deformation field (ablation) | S3D-NeRF · HDTF test | Sync: 5.201 -> 6.514 | Improved |
| use cross-attention audio-visual correlation prior instead of concatenating tri-plane features into deformation (ablation) | S3D-NeRF · HDTF test | M-LMD: 3.196 -> 2.929 | Improved |
| use cross-attention correlation prior instead of feature concatenation (ablation) | S3D-NeRF · HDTF test | SSIM: 0.834 -> 0.829 | Hurt |
| add a deformation module (ablation) | S3D-NeRF · HDTF test | Sync: 0.240 -> 6.514 | Improved |
| add the lip-sync discriminator (ablation) | S3D-NeRF · HDTF test | Sync: 5.649 -> 6.514 | Improved |
| use S3D-NeRF without per-identity training instead of identity-specific NeRFs | talking head synthesis · NeRF-based comparison | fit time (h): ER-NeRF 4.5 -> < 0.01 | Improved |
| use S3D-NeRF instead of ER-NeRF for image similarity | talking head synthesis · NeRF-based comparison | SSIM: 0.884 -> 0.852 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StyleTalk — StyleTalk: One-Shot Talking Head Generation with Controllable Speaking Styles (AAAI 2023) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis (AAAI 2024 · similarity 0.94)
- GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis (ICLR 2023 · similarity 0.93)
- PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis (AAAI 2025 · similarity 0.90)
- SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis (CVPR 2024 · similarity 0.90)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.89)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (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.
