Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions

TL;DR

This paper introduces a learning-free 'half-physics' method that enables 3D human models like SMPL-X to physically interact with environments in real time, maintaining pose fidelity and avoiding interpenetration.

Contribution

It presents a novel half-physics mechanism that embeds kinematic models into physics simulations, allowing realistic interactions without extensive training.

Findings

Eliminates interpenetration issues in 3D human-environment interactions.

Operates in real time with generalization across shapes and motions.

Preserves original kinematic pose fidelity during interactions.

Abstract

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 result, kinematic-based interaction models often suffer from issues such as interpenetration and unrealistic object dynamics. To address this limitation, we introduce a novel approach that embeds SMPL-X into a tangible entity capable of dynamic physical interactions with its surroundings. Specifically, we propose a "half-physics" mechanism that transforms 3D kinematic motion into a physics simulation. Our approach maintains kinematic control over inherent SMPL-X poses while ensuring physically plausible interactions with scenes and objects, effectively eliminating penetration and unrealistic object dynamics. Unlike reinforcement learning-based methods, which demand extensive and complex training, our half-physics method is learning-free and generalizes to any body shape and motion; meanwhile, it operates in real time. Moreover, it preserves the fidelity of the original kinematic motion while seamlessly integrating physical interactions