Saved in:
Bibliographic Details
Main Authors: Han, Bo, Zou, Heqing, Li, Haoyang, Wang, Guangcong, Siong, Chng Eng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.14841
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909263318745088
author Han, Bo
Zou, Heqing
Li, Haoyang
Wang, Guangcong
Siong, Chng Eng
author_facet Han, Bo
Zou, Heqing
Li, Haoyang
Wang, Guangcong
Siong, Chng Eng
contents Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging because of \textbf{1)} generalizable talking-face representation, \textbf{2)} seamless audio-visual transitions, and \textbf{3)} identity-preserved talking faces. Previous works either require minutes of talking-face video training data and expensive test-time optimization for customized talking video editing or directly generate a video sequence without considering in-context information, leading to a poor generalizable representation, or incoherent transitions, or even inconsistent identity. In this paper, we propose an efficient cascaded conditional diffusion-based framework, which consists of two stages: audio to dense-landmark motion and motion to video. \textit{\textbf{In the first stage}}, we first propose a dynamic weighted in-context diffusion module to synthesize dense-landmark motions given an edited audio. \textit{\textbf{In the second stage}}, we introduce a warping-guided conditional diffusion module. The module first interpolates between the start and end frames of the editing interval to generate smooth intermediate frames. Then, with the help of the audio-to-dense motion images, these intermediate frames are warped to obtain coarse intermediate frames. Conditioned on the warped intermedia frames, a diffusion model is adopted to generate detailed and high-resolution target frames, which guarantees coherent and identity-preserved transitions. The cascaded conditional diffusion model decomposes the complex talking editing task into two flexible generation tasks, which provides a generalizable talking-face representation, seamless audio-visual transitions, and identity-preserved faces on a small dataset. Experiments show the effectiveness and superiority of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14841
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text-based Talking Video Editing with Cascaded Conditional Diffusion
Han, Bo
Zou, Heqing
Li, Haoyang
Wang, Guangcong
Siong, Chng Eng
Computer Vision and Pattern Recognition
Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging because of \textbf{1)} generalizable talking-face representation, \textbf{2)} seamless audio-visual transitions, and \textbf{3)} identity-preserved talking faces. Previous works either require minutes of talking-face video training data and expensive test-time optimization for customized talking video editing or directly generate a video sequence without considering in-context information, leading to a poor generalizable representation, or incoherent transitions, or even inconsistent identity. In this paper, we propose an efficient cascaded conditional diffusion-based framework, which consists of two stages: audio to dense-landmark motion and motion to video. \textit{\textbf{In the first stage}}, we first propose a dynamic weighted in-context diffusion module to synthesize dense-landmark motions given an edited audio. \textit{\textbf{In the second stage}}, we introduce a warping-guided conditional diffusion module. The module first interpolates between the start and end frames of the editing interval to generate smooth intermediate frames. Then, with the help of the audio-to-dense motion images, these intermediate frames are warped to obtain coarse intermediate frames. Conditioned on the warped intermedia frames, a diffusion model is adopted to generate detailed and high-resolution target frames, which guarantees coherent and identity-preserved transitions. The cascaded conditional diffusion model decomposes the complex talking editing task into two flexible generation tasks, which provides a generalizable talking-face representation, seamless audio-visual transitions, and identity-preserved faces on a small dataset. Experiments show the effectiveness and superiority of the proposed method.
title Text-based Talking Video Editing with Cascaded Conditional Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.14841