arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.05938cs.GRcs.RO
收藏

先验优先,条件其次:可扩展且可控的手部运动补全

Prior-First, Condition-Second: Scalable and Controllable Hand Motion Completion

The University of Hong Kong(香港大学);Adobe Research(Adobe研究院)

Mingyi Shi, Xuelin Chen, Taku Komura

AI总结:

针对手部运动补全难题,提出先验优先、条件其次框架,先从无结构数据学习通用先验,再引入语义控制,通过分层适配器实现可控性,经评估其在多方面优于基线,还展示了实时推理等特性,适用于动画制作。

摘要:

合成与全身运动和语义标签匹配的手部运动是一项艰巨任务,因其自由度高且缺乏语义标签。为此,我们提出了一种用于身体条件手部运动补全的先验优先、条件其次框架。该框架首先从大规模无结构和无标签运动数据中学习通用的身体 - 手部运动学先验,捕捉全局身体动力学和手部关节之间的内在协调。然后通过在冻结先验之上的轻量级适配引入语义控制,避免为每个控制接口重新学习运动学结构。框架以流式自回归身体 - 手部先验为核心,实时从身体动力学生成连贯、运动学上一致的手部运动。为在有限监督下实现实际可控性,引入语义分层适配器在适当运动学层面注入条件信号。大量评估表明,与端到端条件基线相比,我们的框架提高了运动学合理性、鲁棒性和可控性,尤其在低资源和跨数据集设置中。还展示了实时推理和交互式创作工作流程,突出了其在生产动画管道中的适用性。

英文摘要:

Synthesizing hand motion that matches the full body motion and the semantic labels is a difficult task due to their high degrees of freedom and the lack of semantic labels. To cope with this issue, we propose a prior-first, condition-second framework for body-conditioned hand motion completion. Our framework first learns a generic body-hand kinematic prior from large-scale unstructured and unlabeled motion data, capturing the intrinsic coordination between global body dynamics and hand articulation. Semantic control is then introduced through lightweight adaptation on top of the frozen prior, avoiding the need to relearn kinematic structure for each control interface. Our framework centers on a streaming, autoregressive body-hand prior that generates coherent, kinematically consistent hand motion from body dynamics in real time, using structured kinematic modeling to maintain mechanical body-hand coupling. To enable practical controllability under limited supervision, we introduce semantically-layered adapters that inject conditioning signals at appropriate kinematic levels, supporting both self-supervised attribute control and weakly supervised text-driven control with only a few hours of labeled data. Extensive evaluations demonstrate that our framework improves kinematic plausibility, robustness, and controllability compared to end-to-end conditioned baselines, particularly in low-resource and cross-dataset settings. We further showcase real-time inference and an interactive authoring workflow, highlighting the applicability to production animation pipelines. Homepage: https://AIGAnimation.github.io/HandPrior/

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。

↑