🤖 AI Summary
Existing 3D human avatars struggle to achieve realistic physical interactions, often lacking natural dynamic responses to environments and other agents. This work proposes a novel modeling approach based on the Material Point Method that decouples motion velocity from deformation gradients and integrates a skeletal framework, enabling, for the first time, physics-aware real-time pose tracking and interaction in non-rigid, deformable human bodies. The method allows avatars to maintain target poses under external perturbations, supports closed-loop tracking, and demonstrates stable, diverse, and physically consistent behaviors in both human-object and human-human interactions, significantly enhancing interaction realism.
📝 Abstract
3D human avatars have shown impressive visual fidelity driven by pose-conditioned models, yet they still lack the physical ability required for interactions with each other and environments. Although recent studies have made various attempts to incorporate physical characteristics into 3D avatars, they only exhibit limited physical deformations, often leading to constrained interaction behaviors. To resolve this issue, we present PIAvatar, a framework to simultaneously enable physically aware interactions between avatar-avatar and avatar-environment, and a non-rigid deformable human body simulation. In this work, our key insight is to decouple kinematic velocity from deformation gradient. When external forces act on avatars, the kinematic velocity induces stress which hinders the avatar's ability to achieve a desired pose. In addition, we integrate a skeletal framework within the avatar. It allows estimating its poses and real-time tracking in a closed form, even during non-rigid physical interactions. Our approach is implemented within a conventional Material Point Method framework to ensure physically consistent dynamics. We lastly evaluate the method on both human-object and human-human interaction scenarios to assess its behavior under diverse interaction settings.