Research map / Video / Video generation
ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search
Zhenjie Liu, Jianzhang Lu, Renjie Lu, Cong Liang, Shangfei Wang
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 optical-flow temporal module (OFT) (ablation) | ConsistTalk base model · HDTF (50 clips) | Flicker: 2.2642 -> 0.5288 | Improved |
| add OFT (ablation) | ConsistTalk base model · HDTF (50 clips) | FVD: 228.4 -> 203.9 | Improved |
| add OFT (ablation) | ConsistTalk base model · HDTF (50 clips) | Sync-C: 6.28 -> 5.94 | Hurt |
| add A2I module on top of OFT (ablation) | ConsistTalk base model · HDTF (50 clips) | Beat Align: 1.551 -> 1.624 | Improved |
| add A2I module on top of OFT (ablation) | ConsistTalk base model · HDTF (50 clips) | Diversity: 2.95 -> 3.16 | Improved |
| add A2I module on top of OFT (ablation) | ConsistTalk base model · HDTF (50 clips) | Flicker: 0.5288 -> 0.6583 | Hurt |
| add IC-Init noise search on top of OFT+A2I (ablation) | ConsistTalk base model · HDTF (50 clips) | FVD: 186.5 -> 171.7 | Improved |
| add IC-Init noise search on top of OFT+A2I (ablation) | ConsistTalk base model · HDTF (50 clips) | Flicker: 0.6583 -> 0.4218 | Improved |
| add IC-Init noise search on top of OFT+A2I (ablation) | ConsistTalk base model · HDTF (50 clips) | Sync-C: 6.92 -> 6.83 | Hurt |
| add IC-Init noise search on top of OFT+A2I (ablation) | ConsistTalk base model · HDTF (50 clips) | ID-Dist: 0.1723 -> 0.1743 | Mixed |
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.
- Sonic — Sonic: Shifting Focus to Global Audio Perception in Portrait Animation (CVPR 2025) · better on 3 of 4 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
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.91)
- MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation (AAAI 2025 · similarity 0.91)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.90)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.90)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.90)
- Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model (ICML 2025 · similarity 0.90)
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.
