Research map / Video / Video generation
Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation
Fa-Ting Hong, Zunnan Xu, Zixiang Zhou, Jun Zhou, Xiu Li, Qin Lin, Qinglin Lu, Dan Xu
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 mask-drop strategy (ablation) | ACTalker (audio only) · CelebV-HQ | Sync-C: 4.953 -> 5.317 | Improved |
| add mask-drop strategy (ablation) | ACTalker (audio only) · CelebV-HQ | FVD-Inc: 240.651 -> 232.374 | Improved |
| add mask-drop strategy (ablation) | ACTalker multi-signal · Multi-signal control | control conflict | Improved |
| replace spatial cross-attention with parallel-control mamba layer (ablation) | ACTalker (audio only) · CelebV-HQ | Sync-C: 4.592 -> 5.317 | Improved |
| replace spatial cross-attention with parallel-control mamba layer (ablation) | ACTalker (audio only) · CelebV-HQ | FVD-Inc: 268.512 -> 232.374 | Improved |
| add identity embedding in PCM (ablation) | ACTalker (audio only) · CelebV-HQ | Sync-C: 5.241 -> 5.317 | Improved |
| add identity embedding in PCM (ablation) | ACTalker (audio only) · CelebV-HQ | FVD-Inc: 247.933 -> 232.374 | Improved |
| add facial motion signal to audio control (ablation) | ACTalker · CelebV-HQ | Sync-C: 5.317 -> 5.737 | Improved |
| add facial motion signal to audio control (ablation) | ACTalker · RAVDESS | Sync-C: 5.334 -> 5.511 | Improved |
| ACTalker versus Memo | ACTalker (audio only) · CelebV-HQ | FVD-Inc: 264.596 -> 232.374 | Improved |
| ACTalker versus X-Portrait | ACTalker · VFHQ cross reenactment | Expression Similarity: 0.48 -> 0.57 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EDTalk — EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis (ECCV 2024) · better on 3 of 3 shared results
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
- MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation (AAAI 2025 · similarity 0.88)
- Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling (CVPR 2025 · similarity 0.88)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.88)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.87)
- OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking (NeurIPS 2025 · similarity 0.87)
- AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation (AAAI 2025 · similarity 0.87)
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.
