CVJul 31, 2025

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

arXiv:2507.23778v22 citationsh-index: 24
Originality Incremental advance
AI Analysis

This addresses the limitation of current 3D human models for applications requiring realistic human-environment interactions, though it is incremental as it builds on existing kinematic models like SMPL-X.

The paper tackles the problem of kinematic 3D human models lacking physical interactions, which causes issues like interpenetration and unrealistic object dynamics, by introducing a 'half-physics' mechanism that transforms kinematic motion into physics simulation, eliminating these issues while maintaining real-time operation and motion fidelity.

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

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes