PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction
Humans interact with objects all the time. Enabling a humanoid to learn human-object interaction (HOI) is a key step for future smart animation and intelligent robotics systems. However, recent progress in physics-based HOI requires carefully designed task-specific rewards, making the system unscalable and labor-intensive. This work focuses on dynamic HOI imitation: teaching humanoid dynamic interaction skills through imitating kinematic HOI demonstrations. It is quite challenging because of the complexity of the interaction between body parts and objects and the lack of dynamic HOI data. To handle the above issues, we present PhysHOI, the first physics-based whole-body HOI imitation approach without task-specific reward designs. Except for the kinematic HOI representations of humans and objects, we introduce the contact graph to model the contact relations between body parts and objects explicitly. A contact graph reward is also designed, which proved to be critical for precise HOI imitation. Based on the key designs, PhysHOI can imitate diverse HOI tasks simply yet effectively without prior knowledge. To make up for the lack of dynamic HOI scenarios in this area, we introduce the BallPlay dataset that contains eight whole-body basketball skills. We validate PhysHOI on diverse HOI tasks, including whole-body grasping and basketball skills.
Code (0)
등록된 구현이 없습니다.
Tasks
Human-Object Interaction DetectionObjectSimilar Papers 제목 키워드 기반
Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions
While current general-purpose 3D human models (e.g., SMPL-X) efficiently represent accurate human shape and pose, they lacks the ability to physically interact with the environment due to the kinematic nature. As a resul…
Reinforcement LearningInterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
Achieving realistic simulations of humans interacting with a wide range of objects has long been a fundamental goal. Extending physics-based motion imitation to complex human-object interactions (HOIs) is challenging due…
Human-Object Interaction DetectionObjectEgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video
Humans naturally understand object physics through everyday interactions, but faithfully predicting complex deformable dynamics, such as elastic materials and fabrics, remains a major challenge for computer vision and ro…
Zero-shot GeneralizationInterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically res…
Motion SynthesisTowards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection
Humans detect real-world object anomalies by perceiving, interacting, and reasoning based on object-conditioned physical knowledge. The long-term goal of Industrial Anomaly Detection (IAD) is to enable machines to autono…
Anomaly DetectionObjectVideo UnderstandingVisual Reasoning