Research map / 3D vision / Face and shape
Semi-supervised Speech-driven 3D Facial Animation via Cross-modal Encoding
Peiji Yang, Huawei Wei, Yicheng Zhong, Zhisheng Wang
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 expression de-neutralization (ablation) | Speech-to-Image Transcoder · SelfCollected | lip landmark error (pixel): 3.482 -> 3.241 | Improved |
| add latent cycle consistency loss Lccl (ablation) | Speech-to-Image Transcoder · SelfCollected | lip landmark error (pixel): 3.407 -> 3.241 | Improved |
| joint cross-modal training instead of three-stage pseudo-label pipeline | FaceFormer / VOCA regressors · SelfCollected | lip landmark error (pixel): 3.241 vs 3.613 (FaceFormer*) and 3.790 (VOCA*) | Improved |
| semi-supervised method versus supervised FaceFormer | Ours · SelfCollected | lip vertex error (mm): 3.708 vs 2.690 | Hurt |
| semi-supervised method versus supervised baselines on unseen-language speech | Ours · VOCASET | lip vertex error (mm): 5.102 vs 3.166 (FaceFormer), 4.690 (VOCA) | Hurt |
| semi-supervised model versus FaceFormer in user study lip sync | Ours · VOCASET user study | lip sync preference (%): 15.0 | Hurt |
Closest papers by meaning
- Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications (CVPR 2024 · similarity 0.90)
- Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation (AAAI 2024 · similarity 0.90)
- Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation (NeurIPS 2026 · similarity 0.90)
- Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation (CVPR 2025 · similarity 0.90)
- ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition (AAAI 2025 · similarity 0.90)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 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.
