Research map / Video / Video generation
MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
Liyang Li, Wen Wang, Canyu Zhao, Tianjian Feng, Zhiyue Zhao, Hao Chen, Chunhua Shen
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 |
|---|---|---|---|
| MMControl vs Hallo3 on audio-visual sync despite Hallo3 using ground-truth audio | MMControl · Audio-driven joint generation (200 samples) | Sync-C: 2.550 -> 2.716 | Improved |
| MMControl vs Hallo3 on text alignment | MMControl · Audio-driven joint generation (200 samples) | Text CLIP similarity: 0.2337 -> 0.2546 | Improved |
| MMControl vs Hallo3 on motion intensity | MMControl · Audio-driven joint generation (200 samples) | Dynamic Degree: 0.9184 -> 0.5750 | Hurt |
| MMControl vs Hallo3 on Sync-D | MMControl · Audio-driven joint generation (200 samples) | Sync-D: 10.243 -> 10.506 | Hurt |
| MMControl vs VACE on depth control | MMControl · Depth control (200 samples) | Mean depth MAE x100: 5.35 -> 4.52 | Improved |
| MMControl vs VACE on pose control | MMControl · Pose control | Mean pose MAE x100: 3.29 -> 3.07 | Improved |
| MMControl vs VACE on depth-control aesthetic quality | MMControl · Depth control (200 samples) | Aesthetic Quality: 0.5722 -> 0.5556 | Hurt |
| MMControl vs best baseline on human overall score | MMControl · Human evaluation (4-point scale) | Overall score: 3.22 -> 3.58 | Improved |
| add modality-specific guidance scaling gamma_v=1 to anchor identity (ablation) | MMControl · Decoupled control study (qualitative) | identity fidelity | Improved |
| add gamma_a=1 to preserve reference voice timbre (ablation) | MMControl · Decoupled control study (qualitative) | timbre fidelity | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- Hallo3 — Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer (CVPR 2025) · better on 4 of 6 shared results
- ControlVideo — ControlVideo: Training-free Controllable Text-to-video Generation (ICLR 2024) · better on 2 of 2 shared results
- VideoComposer — VideoComposer: Compositional Video Synthesis with Motion Controllability (NeurIPS 2023) · better on 1 of 1 shared result
- Text2Video-Zero — Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation (ICLR 2025 · similarity 0.90)
- Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation (NeurIPS 2025 · similarity 0.89)
- Native Audio-Visual Alignment for Generation (NeurIPS 2026 · similarity 0.89)
- Read, Watch and Scream! Sound Generation from Text and Video (AAAI 2025 · similarity 0.89)
- Audio-Sync Video Generation with Multi-Stream Temporal Control (NeurIPS 2025 · similarity 0.88)
- MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer (AAAI 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.
