Research map / Video / Video generation
Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback
Xingpei Ma, Shenneng Huang, Jiaran Cai, Yuansheng Guan, Shen Zheng, Hanfeng Zhao, Qiang Zhang, Shunsi 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 Flow-DPO reward feedback (Sync-C based pairs) (ablation) | Ours · HDTF | FID: 29.05 -> 27.63 | Improved |
| add DPO reward feedback (ablation) | Ours · CelebV-HQ | FID: 76.25 -> 66.11 | Improved |
| add DPO reward feedback (ablation) | Ours · HDTF | Sync-C: 7.89 -> 8.15 | Improved |
| add DPO reward feedback (ablation) | Ours · CelebV-HQ | Sync-C: 5.28 -> 5.49 | Improved |
| add DPO reward feedback (ablation) | Ours · CelebV-HQ | FVD: 152.33 -> 133.78 | Improved |
| use LoRA chunked-latent long video training instead of OmniAvatar/Hunyuan extension (ablation) | Ours · long video generation | qualitative | Improved |
| compare with MultiTalk on lip sync | Ours · HDTF | Sync-C: 8.57 vs 8.15 | Hurt |
| compare with MultiTalk on naturalness | Ours · User study | Naturalness MOS: 3.93 vs 3.90 | No clear effect |
Closest papers by meaning
- AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers (CVPR 2025 · similarity 0.89)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.89)
- MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer (AAAI 2025 · similarity 0.89)
- Animate and Sound an Image (CVPR 2025 · similarity 0.89)
- Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation (NeurIPS 2025 · similarity 0.88)
- Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer (CVPR 2025 · similarity 0.88)
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.
