DynamicHOI：用于物理感知手物交互重建的耦合动力学
DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction
浏览论文内容
中文总结 AI 辅助
针对单目RGB视频中手物交互重建的机械不一致问题，提出DynamicHOI框架，通过几何引导扩散细化与耦合手物动力学，引入物理监督和概率先验，在三个数据集上提升重建质量并惠及下游应用。
中文摘要 AI 辅助
我们研究了从单目RGB视频中进行手物交互（HOI）重建的问题，其中部分观测可能产生视觉上合理但机械上不一致的轨迹。现有方法主要强制视觉和几何一致性，对底层交互动力学的约束不足。我们提出了DynamicHOI，一个物理感知的HOI重建框架，结合了几何引导的扩散细化与耦合的手物动力学。几何在空间上为轨迹细化提供视觉证据，而关节逆动力学和牛顿-欧拉动力学推导出手部广义力和物体力旋量，用于动力学级别的监督。我们进一步通过接触力传递耦合手和物体动力学，并恢复主动手部驱动作为交互级别的物理量。我们将其经验幅度分布形式化为概率先验，惩罚不可能的驱动并抑制机械上不合理的重建运动。在三个HOI数据集上的实验显示，手和物体重建均取得一致改进。重建轨迹进一步有益于下游应用，包括手部世界模型生成和机器人操作学习，展示了物理感知HOI建模在重建之外的价值。
英文摘要
We study hand-object interaction (HOI) reconstruction from monocular RGB videos, where partial observations can produce visually plausible yet mechanically inconsistent trajectories. Existing methods mainly enforce visual and geometric agreement, leaving the underlying interaction dynamics insufficiently constrained. We propose DynamicHOI, a physics-aware HOI reconstruction framework combining geometry-grounded diffusion refinement with coupled hand-object dynamics. Geometry spatially grounds visual evidence for trajectory refinement, while articulated inverse dynamics and Newton-Euler dynamics derive hand generalized forces and object wrenches for dynamics-level supervision. We further couple hand and object dynamics through contact-force transfer and recover active hand actuation as an interaction-level physical quantity. We formulate its empirical magnitude distribution into a probabilistic prior that penalizes unlikely actuation and suppresses mechanically implausible reconstructed motion. Experiments on three HOI datasets show consistent improvements in both hand and object reconstruction. The reconstructed trajectories further benefit downstream applications including hand world-model generation and robotic manipulation learning, demonstrating the value of physics-aware HOI modeling beyond reconstruction.
发表机构
- Michigan State University（密歇根州立大学）
机构由 AI 辅助整理，请以论文原文为准。
