Research map / Image generation / Autoregressive and latent generation
DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model
Weiyu Zhao, Chenyang Wang, Liangxiao Hu, Zonglin Li, Wei Yu, Shengping Zhang
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 weight sharing between the two diffusion networks (ablation) | DialoGen · TWH | FDg: 1.895 -> 1.179 | Improved |
| add weight sharing between the two diffusion networks (ablation) | DialoGen · TWH | Divg: 95.72 -> 123.94 | Improved |
| add mutual interaction estimation (MIENet) (ablation) | DialoGen · TWH | FDg: 1.493 -> 1.179 | Improved |
| add mutual interaction estimation (MIENet) (ablation) | DialoGen · TWH | Divg: 100.81 -> 123.94 | Improved |
| add identity-decoupled style input (ablation) | DialoGen · TWH | FDg: 1.705 -> 1.179 | Improved |
| add identity-decoupled style input (ablation) | DialoGen · TWH | FDk: 3.361 -> 2.326 | Improved |
| add identity-decoupled style input (ablation) | DialoGen · TWH | Divg: 131.32 -> 123.94 | Hurt |
| replace one-hot identity encoding with identity-decoupled style (ablation) | DialoGen · TWH | FDg: 1.749 -> 1.179 | Improved |
| add text input (ablation) | DialoGen · TWH | FDg: 1.325 -> 1.179 | Improved |
| add text input (ablation) | DialoGen · TWH | Divk: 155.01 -> 175.23 | Improved |
Closest papers by meaning
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.88)
- MIBURI: Towards Expressive Interactive Gesture Synthesis (CVPR 2026 · similarity 0.87)
- Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control (AAAI 2024 · similarity 0.86)
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.86)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (CVPR 2024 · similarity 0.85)
- Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis (CVPR 2025 · similarity 0.85)
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.
