Saved in:
Bibliographic Details
Main Authors: Wang, Runqi, Chen, Yang, Xu, Sijie, He, Tianyao, Zhu, Wei, Song, Dejia, Chen, Nemo, Tang, Xu, Hu, Yao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.08553
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918085409112064
author Wang, Runqi
Chen, Yang
Xu, Sijie
He, Tianyao
Zhu, Wei
Song, Dejia
Chen, Nemo
Tang, Xu
Hu, Yao
author_facet Wang, Runqi
Chen, Yang
Xu, Sijie
He, Tianyao
Zhu, Wei
Song, Dejia
Chen, Nemo
Tang, Xu
Hu, Yao
contents Face swapping transfers the identity of a source face to a target face while retaining the attributes like expression, pose, hair, and background of the target face. Advanced face swapping methods have achieved attractive results. However, these methods often inadvertently transfer identity information from the target face, compromising expression-related details and accurate identity. We propose a novel method DynamicFace that leverages the power of diffusion models and plug-and-play adaptive attention layers for image and video face swapping. First, we introduce four fine-grained facial conditions using 3D facial priors. All conditions are designed to be disentangled from each other for precise and unique control. Then, we adopt Face Former and ReferenceNet for high-level and detailed identity injection. Through experiments on the FF++ dataset, we demonstrate that our method achieves state-of-the-art results in face swapping, showcasing superior image quality, identity preservation, and expression accuracy. Our framework seamlessly adapts to both image and video domains. Our code and results will be available on the project page: https://dynamic-face.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2501_08553
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors
Wang, Runqi
Chen, Yang
Xu, Sijie
He, Tianyao
Zhu, Wei
Song, Dejia
Chen, Nemo
Tang, Xu
Hu, Yao
Computer Vision and Pattern Recognition
Face swapping transfers the identity of a source face to a target face while retaining the attributes like expression, pose, hair, and background of the target face. Advanced face swapping methods have achieved attractive results. However, these methods often inadvertently transfer identity information from the target face, compromising expression-related details and accurate identity. We propose a novel method DynamicFace that leverages the power of diffusion models and plug-and-play adaptive attention layers for image and video face swapping. First, we introduce four fine-grained facial conditions using 3D facial priors. All conditions are designed to be disentangled from each other for precise and unique control. Then, we adopt Face Former and ReferenceNet for high-level and detailed identity injection. Through experiments on the FF++ dataset, we demonstrate that our method achieves state-of-the-art results in face swapping, showcasing superior image quality, identity preservation, and expression accuracy. Our framework seamlessly adapts to both image and video domains. Our code and results will be available on the project page: https://dynamic-face.github.io/
title DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.08553