PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations

TL;DR

PhysAvatar is a framework that combines inverse rendering and physics simulation to accurately reconstruct and animate clothed 3D human avatars from multi-view videos, capturing clothing physics and enabling realistic renderings.

Contribution

It introduces a novel method integrating inverse rendering with physics simulation to model clothing and appearance of dressed humans from visual data.

Findings

High-quality novel-view renderings of dressed avatars achieved

Effective estimation of clothing physical parameters from video data

Advancement in photorealistic digital human modeling

Abstract

Modeling and rendering photorealistic avatars is of crucial importance in many applications. Existing methods that build a 3D avatar from visual observations, however, struggle to reconstruct clothed humans. We introduce PhysAvatar, a novel framework that combines inverse rendering with inverse physics to automatically estimate the shape and appearance of a human from multi-view video data along with the physical parameters of the fabric of their clothes. For this purpose, we adopt a mesh-aligned 4D Gaussian technique for spatio-temporal mesh tracking as well as a physically based inverse renderer to estimate the intrinsic material properties. PhysAvatar integrates a physics simulator to estimate the physical parameters of the garments using gradient-based optimization in a principled manner. These novel capabilities enable PhysAvatar to create high-quality novel-view renderings of avatars dressed in loose-fitting clothes under motions and lighting conditions not seen in the training data. This marks a significant advancement towards modeling photorealistic digital humans using physically based inverse rendering with physics in the loop. Our project website is at: https://qingqing-zhao.github.io/PhysAvatar