构建物理感知的人物与物体交互数据集，揭示物体属性对动作的影响。
PA-HOI: A Physics-Aware Human and Object Interaction Dataset
- 采集562段人体与35种不同大小重量物体的交互动作
- 发现物体物理属性显著影响人体姿态、速度和运动模式
- 适合机器人、虚拟现实等领域研究真实物理交互
人-物交互（HOI）任务研究物理环境中人与物体的动态交互，为机器人、虚拟现实及人机交互提供重要的生物力学与认知行为基础。然而，现有HOI数据集多关注物体可用性细节，忽视了物体物理属性对人类长期运动的影响。为此，我们提出PA-HOI动作捕捉数据集，重点研究物体物理属性对人类运动动态（包括姿态、移动速度等）的影响。数据集包含562段由不同性别受试者与35种3D物体（尺寸、形状、重量各异）交互的动作序列。该数据集显著扩展了现有数据集的范围，有助于理解不同物体属性如何影响人体姿态、运动速度、运动尺度及交互策略。此外，我们将该数据集与现有动作生成方法结合，验证其在传递真实物理感知方面的有效性。
原文摘要 · Abstract (English)
The Human-Object Interaction (HOI) task explores the dynamic interactions between humans and objects in physical environments, providing essential biomechanical and cognitive-behavioral foundations for fields such as robotics, virtual reality, and human-computer interaction. However, existing HOI data sets focus on details of affordance, often neglecting the influence of physical properties of objects on human long-term motion. To bridge this gap, we introduce the PA-HOI Motion Capture dataset, which highlights the impact of objects' physical attributes on human motion dynamics, including human posture, moving velocity, and other motion characteristics. The dataset comprises 562 motion sequences of human-object interactions, with each sequence performed by subjects of different genders interacting with 35 3D objects that vary in size, shape, and weight. This dataset stands out by significantly extending the scope of existing ones for understanding how the physical attributes of different objects influence human posture, speed, motion scale, and interacting strategies. We further demonstrate the applicability of the PA-HOI dataset by integrating it with existing motion generation methods, validating its capacity to transfer realistic physical awareness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。