LUCAS: Layered Universal Codec Avatars

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Di, Deng, Teng, Nam, Giljoo, Rong, Yu, Pidhorskyi, Stanislav, Li, Junxuan, Saragih, Jason, Metaxas, Dimitris N., Cao, Chen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915202786656256
author Liu, Di
Deng, Teng
Nam, Giljoo
Rong, Yu
Pidhorskyi, Stanislav
Li, Junxuan
Saragih, Jason
Metaxas, Dimitris N.
Cao, Chen
author_facet Liu, Di
Deng, Teng
Nam, Giljoo
Rong, Yu
Pidhorskyi, Stanislav
Li, Junxuan
Saragih, Jason
Metaxas, Dimitris N.
Cao, Chen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19739
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LUCAS: Layered Universal Codec Avatars
Liu, Di
Deng, Teng
Nam, Giljoo
Rong, Yu
Pidhorskyi, Stanislav
Li, Junxuan
Saragih, Jason
Metaxas, Dimitris N.
Cao, Chen
Computer Vision and Pattern Recognition
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.
title LUCAS: Layered Universal Codec Avatars
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.19739