SelfieAvatar: Real-time Head Avatar reenactment from a Selfie Video

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Wei, Yu, Hui, Ding, Derui, Jack, Rachael E., Schyns, Philippe G.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908790302965760
author Liang, Wei
Yu, Hui
Ding, Derui
Jack, Rachael E.
Schyns, Philippe G.
author_facet Liang, Wei
Yu, Hui
Ding, Derui
Jack, Rachael E.
Schyns, Philippe G.
contents Head avatar reenactment focuses on creating animatable personal avatars from monocular videos, serving as a foundational element for applications like social signal understanding, gaming, human-machine interaction, and computer vision. Recent advances in 3D Morphable Model (3DMM)-based facial reconstruction methods have achieved remarkable high-fidelity face estimation. However, on the one hand, they struggle to capture the entire head, including non-facial regions and background details in real time, which is an essential aspect for producing realistic, high-fidelity head avatars. On the other hand, recent approaches leveraging generative adversarial networks (GANs) for head avatar generation from videos can achieve high-quality reenactments but encounter limitations in reproducing fine-grained head details, such as wrinkles and hair textures. In addition, existing methods generally rely on a large amount of training data, and rarely focus on using only a simple selfie video to achieve avatar reenactment. To address these challenges, this study introduces a method for detailed head avatar reenactment using a selfie video. The approach combines 3DMMs with a StyleGAN-based generator. A detailed reconstruction model is proposed, incorporating mixed loss functions for foreground reconstruction and avatar image generation during adversarial training to recover high-frequency details. Qualitative and quantitative evaluations on self-reenactment and cross-reenactment tasks demonstrate that the proposed method achieves superior head avatar reconstruction with rich and intricate textures compared to existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18851
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SelfieAvatar: Real-time Head Avatar reenactment from a Selfie Video
Liang, Wei
Yu, Hui
Ding, Derui
Jack, Rachael E.
Schyns, Philippe G.
Computer Vision and Pattern Recognition
Head avatar reenactment focuses on creating animatable personal avatars from monocular videos, serving as a foundational element for applications like social signal understanding, gaming, human-machine interaction, and computer vision. Recent advances in 3D Morphable Model (3DMM)-based facial reconstruction methods have achieved remarkable high-fidelity face estimation. However, on the one hand, they struggle to capture the entire head, including non-facial regions and background details in real time, which is an essential aspect for producing realistic, high-fidelity head avatars. On the other hand, recent approaches leveraging generative adversarial networks (GANs) for head avatar generation from videos can achieve high-quality reenactments but encounter limitations in reproducing fine-grained head details, such as wrinkles and hair textures. In addition, existing methods generally rely on a large amount of training data, and rarely focus on using only a simple selfie video to achieve avatar reenactment. To address these challenges, this study introduces a method for detailed head avatar reenactment using a selfie video. The approach combines 3DMMs with a StyleGAN-based generator. A detailed reconstruction model is proposed, incorporating mixed loss functions for foreground reconstruction and avatar image generation during adversarial training to recover high-frequency details. Qualitative and quantitative evaluations on self-reenactment and cross-reenactment tasks demonstrate that the proposed method achieves superior head avatar reconstruction with rich and intricate textures compared to existing approaches.
title SelfieAvatar: Real-time Head Avatar reenactment from a Selfie Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18851