Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ki, Taekyung, Min, Dongchan
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2305.00521
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916120219353088
author Ki, Taekyung
Min, Dongchan
author_facet Ki, Taekyung
Min, Dongchan
contents In this paper, we present StyleLipSync, a style-based personalized lip-sync video generative model that can generate identity-agnostic lip-synchronizing video from arbitrary audio. To generate a video of arbitrary identities, we leverage expressive lip prior from the semantically rich latent space of a pre-trained StyleGAN, where we can also design a video consistency with a linear transformation. In contrast to the previous lip-sync methods, we introduce pose-aware masking that dynamically locates the mask to improve the naturalness over frames by utilizing a 3D parametric mesh predictor frame by frame. Moreover, we propose a few-shot lip-sync adaptation method for an arbitrary person by introducing a sync regularizer that preserves lip-sync generalization while enhancing the person-specific visual information. Extensive experiments demonstrate that our model can generate accurate lip-sync videos even with the zero-shot setting and enhance characteristics of an unseen face using a few seconds of target video through the proposed adaptation method.
format Preprint
id arxiv_https___arxiv_org_abs_2305_00521
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle StyleLipSync: Style-based Personalized Lip-sync Video Generation
Ki, Taekyung
Min, Dongchan
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
In this paper, we present StyleLipSync, a style-based personalized lip-sync video generative model that can generate identity-agnostic lip-synchronizing video from arbitrary audio. To generate a video of arbitrary identities, we leverage expressive lip prior from the semantically rich latent space of a pre-trained StyleGAN, where we can also design a video consistency with a linear transformation. In contrast to the previous lip-sync methods, we introduce pose-aware masking that dynamically locates the mask to improve the naturalness over frames by utilizing a 3D parametric mesh predictor frame by frame. Moreover, we propose a few-shot lip-sync adaptation method for an arbitrary person by introducing a sync regularizer that preserves lip-sync generalization while enhancing the person-specific visual information. Extensive experiments demonstrate that our model can generate accurate lip-sync videos even with the zero-shot setting and enhance characteristics of an unseen face using a few seconds of target video through the proposed adaptation method.
title StyleLipSync: Style-based Personalized Lip-sync Video Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2305.00521