Research map / 3D vision / Face and shape
EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head
Qianyun He, Xinya Ji, Yicheng Gong, Yuanxun Lu, Zhengyu Diao, Linjia Huang, Yao Yao, Siyu Zhu, Zhan Ma, Songcen Xu, Xiaofei Wu, Zixiao Zhang and 2 more
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 intermediate 3D geometry stage (speech-to-geometry-to-appearance) instead of direct speech-to-appearance (ablation) | EmoTalk3D · EmoTalk3D test split | LMD: 10.83 -> 3.62 | Improved |
| add intermediate geometry stage (ablation) | EmoTalk3D · EmoTalk3D test split | PSNR: 24.30 -> 21.22 | Hurt |
| add emotion extractor and emotion labels in S2GNet (ablation) | EmoTalk3D · EmoTalk3D test split | LMD: 5.60 -> 3.62 | Improved |
| add FeatureNet for dynamic Gaussian appearance (ablation) | EmoTalk3D · EmoTalk3D test split | LMD: 4.93 -> 3.62 | Improved |
| add FeatureNet for dynamic Gaussian appearance (ablation) | EmoTalk3D · EmoTalk3D test split | CPBD: 0.35 -> 0.30 | Hurt |
| add FeatureNet for dynamic Gaussian appearance (ablation) | EmoTalk3D · EmoTalk3D test split | PSNR: 20.85 -> 21.22 | Improved |
| use EmoTalk3D instead of DreamTalk for sharpness | EmoTalk3D · EmoTalk3D test split | CPBD: 0.38 -> 0.30 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MeshTalk — MeshTalk: 3D Face Animation From Speech Using Cross-Modality Disentanglement (ICCV 2021) · better on 0 of 1 shared result
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
- EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization (CVPR 2026 · similarity 0.92)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025 · similarity 0.90)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.89)
- PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis (AAAI 2025 · similarity 0.89)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.89)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · 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.
