LUCAS: Layered Universal Codec Avatars
This work advances 3D head avatar reconstruction for applications like virtual reality and gaming, though it appears incremental by building on prior universal prior models with a layered approach.
The paper tackled the problem of photorealistic 3D head avatar reconstruction by addressing challenges in dynamic face-hair interactions and cross-identity generalization, resulting in LUCAS outperforming existing models in quantitative and qualitative assessments, including zero-shot driving scenarios.
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.