PICA: Physics-Integrated Clothed Avatar

TL;DR

PICA introduces a physics-aware, separate modeling approach for clothed human avatars, enabling high-fidelity, realistic animations of loose clothing with accurate dynamics, surpassing previous neural rendering methods.

Contribution

It presents a novel physics-integrated framework using separate 3D Gaussian Splatting models and a GNN-based physics module for realistic clothed avatar animation.

Findings

Achieves high-fidelity rendering in complex poses

Outperforms previous methods in clothing dynamics accuracy

Handles loose clothing and sliding effects effectively

Abstract

We introduce PICA, a novel representation for high-fidelity animatable clothed human avatars with physics-accurate dynamics, even for loose clothing. Previous neural rendering-based representations of animatable clothed humans typically employ a single model to represent both the clothing and the underlying body. While efficient, these approaches often fail to accurately represent complex garment dynamics, leading to incorrect deformations and noticeable rendering artifacts, especially for sliding or loose garments. Furthermore, previous works represent garment dynamics as pose-dependent deformations and facilitate novel pose animations in a data-driven manner. This often results in outcomes that do not faithfully represent the mechanics of motion and are prone to generating artifacts in out-of-distribution poses. To address these issues, we adopt two individual 3D Gaussian Splatting (3DGS) models with different deformation characteristics, modeling the human body and clothing separately. This distinction allows for better handling of their respective motion characteristics. With this representation, we integrate a graph neural network (GNN)-based clothed body physics simulation module to ensure an accurate representation of clothing dynamics. Our method, through its carefully designed features, achieves high-fidelity rendering of clothed human bodies in complex and novel driving poses, significantly outperforming previous methods under the same settings.