Research map / 3D vision / Face and shape
Talking Together: Synthesizing Co-Located 3D Conversations from Audio
Mengyi Shan, Shouchieh Chang, Ziqian Bai, Shichen Liu, Yinda Zhang, Luchuan Song, Rohit Pandey, Sean Fanello, Zeng Huang
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 second-stage fine-tuning on high-quality lip data (ablation) | dual-stream diffusion model · Dyadic test set, ablation | FD: 60.12 -> 21.71 | Improved |
| add second-stage fine-tuning on high-quality lip data (ablation) | dual-stream diffusion model · Dyadic test set, ablation | Lip-Sync preference (%): 17.2 -> 78.3 | Improved |
| add conversation data pre-training on top of single-person data (ablation) | dual-stream diffusion model · Dyadic test set, ablation | FD: 50.45 -> 21.71 | Improved |
| add speaker role embedding (ablation) | dual-stream diffusion model · Dyadic test set, ablation | FD: 35.92 -> 21.71 | Improved |
| add inter-speaker cross-attention (ablation) | dual-stream diffusion model · Dyadic test set, ablation | P-FD: 40.87 -> 22.56 | Improved |
| add auxiliary eye gaze loss on high head-rotation samples (ablation) | dual-stream diffusion model · Dyadic test set, ablation | P-FD: 42.90 -> 22.56 | Improved |
| add auxiliary eye gaze loss (ablation) | dual-stream diffusion model · Dyadic test set, ablation | TRAN MSE: 2.59 -> 1.50 | Improved |
| train on dyadic conversation data instead of single-person model | dual-stream model vs Ours (Single) · Dyadic test set (Table 2) | vMSE (FULL): 2.23 -> 2.28 | Mixed |
| use full interactive model instead of best conversation baseline DualTalk | dyadic generation · Dyadic test set (Table 2) | FD (FULL): 28.41 -> 10.43 | Improved |
| retrieval-based listener baselines vs ours on rotation and translation diversity | listener generation · Dyadic test set (Table 2) | SID (LIS): 2.98 (Listen-R) vs 2.45 | No clear effect |
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.
- DualTalk — DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations (CVPR 2025) · better on 4 of 4 shared results
- CodeTalker — CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior (CVPR 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
- DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations (CVPR 2025 · similarity 0.90)
- INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations (CVPR 2025 · similarity 0.90)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.89)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025 · similarity 0.88)
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.88)
- Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation (NeurIPS 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.
