MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Mengting, Li, Yante, Varanka, Tuomas, Jiang, Yan, Zhao, Guoying
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908617674850304
author Wei, Mengting
Li, Yante
Varanka, Tuomas
Jiang, Yan
Zhao, Guoying
author_facet Wei, Mengting
Li, Yante
Varanka, Tuomas
Jiang, Yan
Zhao, Guoying
contents In this study, we propose a method for video face reenactment that integrates a 3D face parametric model into a latent diffusion framework, aiming to improve shape consistency and motion control in existing video-based face generation approaches. Our approach employs the FLAME (Faces Learned with an Articulated Model and Expressions) model as the 3D face parametric representation, providing a unified framework for modeling face expressions and head pose. This not only enables precise extraction of motion features from driving videos, but also contributes to the faithful preservation of face shape and geometry. Specifically, we enhance the latent diffusion model with rich 3D expression and detailed pose information by incorporating depth maps, normal maps, and rendering maps derived from FLAME sequences. These maps serve as motion guidance and are encoded into the denoising UNet through a specifically designed Geometric Guidance Encoder (GGE). A multi-layer feature fusion module with integrated self-attention mechanisms is used to combine facial appearance and motion latent features within the spatial domain. By utilizing the 3D face parametric model as motion guidance, our method enables parametric alignment of face identity between the reference image and the motion captured from the driving video. Experimental results on benchmark datasets show that our method excels at generating high-quality face animations with precise expression and head pose variation modeling. In addition, it demonstrates strong generalization performance on out-of-domain images. Code is publicly available at https://github.com/weimengting/MagicPortrait.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21497
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
Wei, Mengting
Li, Yante
Varanka, Tuomas
Jiang, Yan
Zhao, Guoying
Computer Vision and Pattern Recognition
In this study, we propose a method for video face reenactment that integrates a 3D face parametric model into a latent diffusion framework, aiming to improve shape consistency and motion control in existing video-based face generation approaches. Our approach employs the FLAME (Faces Learned with an Articulated Model and Expressions) model as the 3D face parametric representation, providing a unified framework for modeling face expressions and head pose. This not only enables precise extraction of motion features from driving videos, but also contributes to the faithful preservation of face shape and geometry. Specifically, we enhance the latent diffusion model with rich 3D expression and detailed pose information by incorporating depth maps, normal maps, and rendering maps derived from FLAME sequences. These maps serve as motion guidance and are encoded into the denoising UNet through a specifically designed Geometric Guidance Encoder (GGE). A multi-layer feature fusion module with integrated self-attention mechanisms is used to combine facial appearance and motion latent features within the spatial domain. By utilizing the 3D face parametric model as motion guidance, our method enables parametric alignment of face identity between the reference image and the motion captured from the driving video. Experimental results on benchmark datasets show that our method excels at generating high-quality face animations with precise expression and head pose variation modeling. In addition, it demonstrates strong generalization performance on out-of-domain images. Code is publicly available at https://github.com/weimengting/MagicPortrait.
title MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.21497