Research map / Video / Video generation
Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait
Chaolong Yang, Kai Yao, Xi Yang, Chenru Jiang, Weiguang Zhao, Jie Sun, Guangliang Cheng, Yifei Zhang, Bin Dong, Kaizhu Huang
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 reference keypoint x_c (ablation) | KDTalker · HDTF | LSE-C: 6.656 -> 7.326 | Improved |
| add spatiotemporal attention (ablation) | KDTalker · HDTF | LSE-C: 1.360 -> 7.326 | Improved |
| add spatiotemporal attention (ablation) | KDTalker · HDTF | Head motion diversity: 2.292 -> 0.760 | Mixed |
| add RoPE (ablation) | KDTalker · HDTF | LSE-C: 7.225 -> 7.326 | Improved |
| add RoPE (ablation) | KDTalker · HDTF | Head motion diversity: 0.706 -> 0.760 | Improved |
| use diffusion generator instead of VAE (ablation) | KDTalker · HDTF | LSE-C: 0.665 -> 7.326 | Improved |
| use diffusion generator instead of VAE+GAN (ablation) | KDTalker · HDTF | LSE-C: 1.232 -> 7.326 | Improved |
| use LivePortrait renderer instead of Face-vid2vid (ablation) | KDTalker · HDTF | LSE-C: 5.579 -> 7.326 | Improved |
| use LivePortrait renderer instead of Face-vid2vid (ablation) | KDTalker · HDTF | FID: 8.625 -> 9.756 | Hurt |
| increase DDIM steps from 1 to 5 (ablation) | KDTalker · HDTF | LSE-C: 0.817 -> 7.455 | Improved |
| increase DDIM steps from 5 to 50 (ablation) | KDTalker · HDTF | FID: 10.226 -> 9.756 | Improved |
| increase DDIM steps from 50 to 200 (ablation) | KDTalker · HDTF | LSE-C: 7.326 -> 7.221 | Hurt |
Closest papers by meaning
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.89)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.88)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.88)
- Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer (CVPR 2025 · similarity 0.88)
- PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis (AAAI 2025 · similarity 0.88)
- Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation (CVPR 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.
