**Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation**

> Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging. Prior speech-driven gesture models emphasize audio-gesture alignment but do not explicitly account for posture constraints or surrounding objects, failing to capture the inherent correlation between body gestures and the physical space. We present Puppeteer, a postur...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：论文
- **发布时间**：2026-09-10 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.00369)