Research map / Video / Video generation
Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation
Baiqin Wang, Sen Chen, Jiankuo Zhao, Xiangyu Liu, Zhen Lei, Xiangyu Zhu
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 motion feedback from other participants in RCE (ablation) | InterTalk · InterTalk dataset | FD: 29.72 -> 22.67 | Improved |
| add iterative generation strategy (ablation) | InterTalk · InterTalk dataset | FD: 24.26 -> 22.67 | Improved |
| add iterative generation strategy (ablation) | InterTalk · InterTalk dataset | FPS: 34.67 -> 31.23 | Hurt |
| add motion disentanglement with sync-enhancer (ablation) | InterTalk · InterTalk dataset | Sync-C: 7.58 -> 8.30 | Improved |
| add 3D face-based data augmentation (ablation) | InterTalk · InterTalk dataset | FD: 38.67 -> 22.67 | Improved |
| add 3D face-based data augmentation (ablation) | InterTalk · InterTalk dataset | SID: 1.95 -> 4.28 | Improved |
| use InterTalk instead of MultiTalk | InterTalk · InterTalk dataset | FPS: 0.61 -> 31.23 | Improved |
| use InterTalk instead of MultiTalk | InterTalk · InterTalk dataset | SID: 5.14 -> 4.28 | Hurt |
| use InterTalk instead of Sonic | InterTalk · HDTF | Sync-D: 6.88 -> 6.91 | No clear effect |
| use InterTalk instead of Sonic | InterTalk · HDTF | FVD: 204.55 -> 178.73 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Sonic — Sonic: Shifting Focus to Global Audio Perception in Portrait Animation (CVPR 2025) · better on 4 of 5 shared results
- ARIG — ARIG: Autoregressive Interactive Head Generation for Real-time Conversations (ICCV 2025) · better on 2 of 2 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
- MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes (NeurIPS 2024 · similarity 0.89)
- DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations (CVPR 2025 · similarity 0.89)
- INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations (CVPR 2025 · similarity 0.88)
- AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation (AAAI 2025 · similarity 0.88)
- Faces that Speak: Jointly Synthesising Talking Face and Speech from Text (CVPR 2024 · similarity 0.88)
- Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation (NeurIPS 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.
