Research map / Video / Video generation
Audio-Driven Neural Gesture Reenactment With Video Motion Graphs
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| combine mesh-based and optical-flow warping instead of using either alone (ablation) | Pose-aware video blending · Personal story dataset | IE: 0.87 -> 0.76; 0.97 -> 0.76 | Helped |
| combine mesh-based and optical-flow warping instead of using either alone (ablation) | Pose-aware video blending · TED-talks dataset | IE: 1.36 -> 0.93; 1.25 -> 0.93 | Helped |
| use audio-based graph search rather than random motion-graph paths (ablation) | Audio-driven reenactment · Personal story dataset user study | preference: 61% vs. 39% | Helped |
| use mesh-based and optical-flow warping together rather than mesh-based warping only (ablation) | Pose-aware video blending · Personal story dataset | PSNR: 35.2 -> 36.1 | Helped |
| use mesh-based and optical-flow warping together rather than optical-flow warping only (ablation) | Pose-aware video blending · Personal story dataset | PSNR: 34.6 -> 36.1 | Helped |
| use mesh-based and optical-flow warping together rather than mesh-based warping only (ablation) | Pose-aware video blending · TED-talks dataset | PSNR: 27.9 -> 30.7 | Helped |
| use mesh-based and optical-flow warping together rather than optical-flow warping only (ablation) | Pose-aware video blending · TED-talks dataset | PSNR: 28.2 -> 30.7 | Helped |
| use mesh-based and optical-flow warping together rather than mesh-based warping only (ablation) | Pose-aware video blending · TED-talks dataset | FID: 11.5 -> 11.8 | Hurt |
Closest papers by meaning
- TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation (ICLR 2025 · similarity 0.91)
- Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement (CVPR 2025 · similarity 0.87)
- Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model (CVPR 2024 · similarity 0.87)
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.85)
- Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model (CVPR 2025 · similarity 0.85)
- Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation (CVPR 2024 · similarity 0.84)
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.