Research map / Video / Video generation
Speech Drives Templates: Co-Speech Gesture Synthesis With Learned Templates
Shenhan Qian, Zhi Tu, Yihao Zhi, Wen Liu, Shenghua Gao
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 clip-wise template vectors learned by back-propagation (ablation) | UNet gesture generator without templates · Oliver | FTD: 1.66 -> 1.26 | Improved |
| add clip-wise template vectors learned by back-propagation (ablation) | UNet gesture generator without templates · Oliver | normalized lip-sync error: 0.17 -> 0.17 | No clear effect |
| learn clip-wise templates with a VAE instead of back-propagation (ablation) | template-BP clip-wise · Oliver | FTD: 1.26 -> 0.92 | Improved |
| use frame-wise instead of clip-wise templates (ablation) | template-BP · Oliver | normalized lip-sync error: 0.17 -> 0.21 | Hurt |
| use frame-wise instead of clip-wise templates (ablation) | template-BP · Oliver | FTD: 1.26 -> 0.78 | Improved |
| replace batch norm with instance norm (ablation) | UNet without templates · Oliver | FTD: 7.01 -> 1.54 | Improved |
| replace batch norm with instance norm (ablation) | UNet without templates · Oliver | normalized lip-sync error: 0.20 -> 0.19 | Improved |
| use transposed instance norm instead of plain instance norm (ablation) | UNet without templates · Oliver | FTD: 1.54 -> 1.53 | No clear effect |
| add hierarchical body representation (ablation) | UNet without templates (IN*) · Oliver | normalized lip-sync error: 0.19 -> 0.17 | Improved |
| add hierarchical body representation (ablation) | UNet without templates (IN*) · Oliver | FTD: 1.53 -> 1.66 | Hurt |
| use template-VAE instead of MoGlow | MoGlow · Oliver | FTD: 2.28 -> 0.92 | Improved |
| use template-VAE instead of Speech2Gesture | Speech2Gesture · Oliver | FTD: 8.30 -> 0.92 | Improved |
Closest papers by meaning
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.91)
- Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model (CVPR 2024 · similarity 0.90)
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.90)
- Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement (CVPR 2025 · similarity 0.90)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (CVPR 2024 · similarity 0.90)
- EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling (CVPR 2024 · 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.
