PA-HOI: A Physics-Aware Human and Object Interaction Dataset

TL;DR

This paper introduces PA-HOI, a new motion capture dataset that emphasizes the influence of physical object properties on human motion, aiding advancements in robotics, VR, and HCI.

Contribution

The paper presents the PA-HOI dataset, which uniquely captures the impact of object physical attributes on human motion dynamics, extending existing HOI datasets.

Findings

The dataset includes 562 motion sequences with diverse objects.

Physical attributes significantly affect human posture and motion.

Integration with motion generation methods shows improved realism.

Abstract

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.