PICA: Physics-Integrated Clothed Avatar
This addresses the challenge of realistic clothing simulation in digital avatars for applications like animation and VR, though it appears incremental as it builds on existing neural rendering and physics techniques.
The authors tackled the problem of inaccurate garment dynamics and rendering artifacts in animatable clothed human avatars by introducing PICA, a representation that uses separate 3D Gaussian Splatting models for body and clothing integrated with a GNN-based physics simulation, achieving high-fidelity rendering in novel poses and significantly outperforming previous methods.
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.