Research map / Video / Video generation
Audio-Driven Co-Speech Gesture Video Generation
Xian Liu, Qianyi Wu, Hang Zhou, Yuanqi Du, Wayne Wu, Dahua Lin, Ziwei 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 |
|---|---|---|---|
| quantize gesture motion into codebooks (vs predicting continuous motion) (ablation) | ANGIE · PATS | FGD: 5.86 -> 1.35 | Improved |
| quantize position-irrelevant relative motion (delta mu, delta L) instead of absolute (ablation) | ANGIE · PATS | L1 reconstruction: 0.058 -> 0.037 | Improved |
| quantize relative delta mu only vs relative delta L only (ablation) | ANGIE · PATS | L1 reconstruction: 0.052 -> 0.043 | Improved |
| add motion refinement residual network (ablation) | ANGIE · PATS | beat consistency: 0.58 -> 0.72 | Improved |
| add motion refinement residual network (ablation) | ANGIE · PATS | FGD: 1.39 -> 1.35 | No clear effect |
| add motion refinement residual network (ablation) | ANGIE · PATS | perceptual loss: 48.1 -> 42.9 | Improved |
| remove cholesky decomposition constraint (ablation) | ANGIE · PATS | image generation | Hurt |
| use ANGIE vs SDT baseline | SDT · PATS Oliver | FGD: 1.04 -> 0.88 | Improved |
| use unseen audio at test time | ANGIE · PATS | FGD: 1.35 -> 1.46 | Hurt |
| concatenate text features with audio (ablation) | ANGIE · PATS | FGD: 1.35 -> 1.30 | Improved |
Closest papers by meaning
- Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model (CVPR 2024 · similarity 0.94)
- Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement (CVPR 2025 · similarity 0.93)
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.91)
- TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation (ICLR 2025 · similarity 0.90)
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.89)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (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.
