StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
Real-time co-speech gesture generation must produce 3D motion clip by clip as speech arrives. Existing streaming methods are open-loop: each clip depends on past context, but the model cannot check or correct its trajectory. Small errors therefore accumulate and cause drift over long sequences. We observe that this failure is mainly caused by the lack of a forward constraint rather than poor short-clip quality. A plausible key pose at the end of each clip provides a destination anchor that limits drift. Based on this observation, we propose StreamTalk, a closed-loop framework with a periodic generate-retrieve-refine cycle. Streaming Pose-Guided Generation first predicts a coarse clip, ret...
| Authors | Xiangyue Zhang, Jianfang Li, Jiaxu Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 3 August 2026 |
| Last updated at source | 3 August 2026 |
Connected in the knowledge graph
- X-Zhang/StreamTalk-Inference-DataDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.