Research map / Image generation / Autoregressive and latent generation
Audio-Driven Stylized Gesture Generation with Flow-Based Model
Sheng Ye, Yu-Hui Wen, Yanan Sun, Ying He, Ziyang Zhang, Yaoyuan Wang, Weihua He, Yong-Jin Liu
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 gesture perceptual loss (ablation) | Ours · TED | FGD: 4.62 -> 3.30 | Improved |
| add gesture perceptual loss (ablation) | Ours · TED | Diversity: 51 -> 52 | Improved |
| add gesture perceptual loss (ablation) | Ours · TED | PCK: 0.845 -> 0.850 | Improved |
| add global encoder (ablation) | Ours · TED | FGD: 6.26 -> 3.30 | Improved |
| add global encoder (ablation) | Ours · TED | Diversity: 50 -> 52 | Improved |
| add global encoder (ablation) | Ours · TED | PCK: 0.848 -> 0.850 | No clear effect |
| add both global encoder and Lgp to GRU MoGlow baseline (ablation) | Ours · TED | FGD: 6.10 -> 3.30 | Improved |
| add Lgp without the global encoder (ablation) | Ours · TED | FGD: 6.10 -> 6.26 | Hurt |
| replace LSTM with GRU in coupling layers (ablation) | Ours · TED | quality | No clear effect |
| use flow model with global encoder instead of MoGlow (ablation) | Ours · Trinity | FGD: 7.61 -> 6.76 | Improved |
| use flow model with global encoder instead of MoGlow (ablation) | Ours · TED (15-speaker subset) | CHI: 908.47 -> 1149.34 | Improved |
| use flow model with global encoder instead of MoGlow (ablation) | Ours · TED (15-speaker subset) | SCoeff: 0.443 -> 0.517 | Improved |
Closest papers by meaning
- 🎧MOSPA: Human Motion Generation Driven by Spatial Audio (NeurIPS 2025 · similarity 0.87)
- Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion (CVPR 2024 · similarity 0.86)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (CVPR 2024 · similarity 0.86)
- Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control (AAAI 2024 · similarity 0.86)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.86)
- Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement (CVPR 2025 · similarity 0.86)
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.
