LUCAS: Layered Universal Codec Avatars

TL;DR

LUCAS introduces a layered, mesh-based universal prior model for 3D head avatars that disentangles face and hair, enabling more realistic, dynamic, and cross-identity generalizable avatar reconstructions in real-time.

Contribution

It is the first layered, mesh-based universal prior model that separates face and hair modeling, improving realism and dynamic performance in 3D avatar reconstruction.

Findings

Outperforms existing models in quantitative assessments.

Achieves real-time rendering on devices.

Handles head pose, expression, and hairstyle variations effectively.

Abstract

Photorealistic 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions and achieving cross-identity generalization, particularly during expressions and head movements. We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that disentangles face and hair through a layered representation. Unlike previous UPMs that treat hair as an integral part of the head, our approach separates the modeling of the hairless head and hair into distinct branches. LUCAS is the first to introduce a mesh-based UPM, facilitating real-time rendering on devices. Our layered representation also improves the anchor geometry for precise and visually appealing Gaussian renderings. Experimental results indicate that LUCAS outperforms existing single-mesh and Gaussian-based avatar models in both quantitative and qualitative assessments, including evaluations on held-out subjects in zero-shot driving scenarios. LUCAS demonstrates superior dynamic performance in managing head pose changes, expression transfer, and hairstyle variations, thereby advancing the state-of-the-art in 3D head avatar reconstruction.