PhysHead: Simulation-Ready Gaussian Head Avatars

TL;DR

PhysHead introduces a hybrid 3D Gaussian layered model for realistic, animatable head avatars with dynamic hair, learned from multi-view video, enabling photorealistic, physics-based hair motion.

Contribution

The paper presents PhysHead, a novel hybrid representation combining a 3D Gaussian layered model with physics simulation for realistic, animatable head avatars with dynamic hair.

Findings

Enables photorealistic avatars with wind-blown hair motion.

Outperforms existing methods in capturing natural hair dynamics.

Uses VLM-based models to handle occluded appearance regions during training.

Abstract

Realistic digital avatars require expressive and dynamic hair motion; however, most existing head avatar methods assume rigid hair movement. These methods often fail to disentangle hair from the head, representing it as a simple outer shell and failing to capture its natural volumetric behavior. In this paper, we address these limitations by introducing PhysHead, a hybrid representation for animatable head avatars with realistic hair dynamics learned from multi-view video. At the core is a 3D Gaussian-based layered representation of the head. Our approach combines a 3D parametric mesh for the head with strand-based hair, which can be directly simulated using physics engines. For the appearance model, we employ Gaussian primitives attached to both the head mesh and hair segments. This representation enables the creation of photorealistic head avatars with dynamic hair behavior, such as wind-blown motion, overcoming the constraints of rigid hair in existing methods. However, these animation capabilities also require new training schemes. In particular, we propose the use of VLM-based models to generate appearance of regions that are occluded in the dynamic training sequences. In quantitative and qualitative studies, we demonstrate the capabilities of the proposed model and compare it with existing baselines. We show that our method can synthesize physically plausible hair motion besides expression and camera control.