HandX：扩展双臂运动和交互生成
HandX: Scaling Bimanual Motion and Interaction Generation
AI总结：
本文提出HandX，通过整合数据、标注和评估，解决双臂运动生成中精细指节动态和协作的不足，验证了大模型在生成高质量双臂运动中的有效性。
摘要：
合成人类运动已取得显著进展，但逼真手部运动和双臂交互仍待深入研究。全身模型常忽略驱动灵巧行为的细粒度线索，如手指关节运动、接触时机和手间协调。现有资源缺乏高保真双臂序列，无法捕捉细微指节动态和协作。为此，我们提出HandX，构建统一基础，整合并过滤现有数据集，收集新运动捕捉数据集，针对被忽视的双臂交互进行详细指节动态记录。为实现可扩展标注，我们引入解耦策略，提取代表性运动特征，如接触事件和手指弯曲，并利用大语言模型推理生成细粒度、语义丰富的描述。基于所得数据和标注，我们对扩散模型和自回归模型进行基准测试，验证了高质量灵巧运动生成，支持我们新提出的手部聚焦指标。进一步观察到清晰的扩展趋势：在更大、更高质量数据集上训练的更大模型，生成更语义一致的双臂运动。我们的数据集已发布以支持未来研究。
英文摘要：
Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that drive dexterous behavior, finger articulation, contact timing, and inter-hand coordination, and existing resources lack high-fidelity bimanual sequences that capture nuanced finger dynamics and collaboration. To fill this gap, we present HandX, a unified foundation spanning data, annotation, and evaluation. We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics. For scalable annotation, we introduce a decoupled strategy that extracts representative motion features, e.g., contact events and finger flexion, and then leverages reasoning from large language models to produce fine-grained, semantically rich descriptions aligned with these features. Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes. Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics. We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion. Our dataset is released to support future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
