Video Editing for Audio-Visual Dubbing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manela, Binyamin, Gannot, Sharon, Fetyaya, Ethan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915312559980544
author Manela, Binyamin
Gannot, Sharon
Fetyaya, Ethan
author_facet Manela, Binyamin
Gannot, Sharon
Fetyaya, Ethan
contents Visual dubbing, the synchronization of facial movements with new speech, is crucial for making content accessible across different languages, enabling broader global reach. However, current methods face significant limitations. Existing approaches often generate talking faces, hindering seamless integration into original scenes, or employ inpainting techniques that discard vital visual information like partial occlusions and lighting variations. This work introduces EdiDub, a novel framework that reformulates visual dubbing as a content-aware editing task. EdiDub preserves the original video context by utilizing a specialized conditioning scheme to ensure faithful and accurate modifications rather than mere copying. On multiple benchmarks, including a challenging occluded-lip dataset, EdiDub significantly improves identity preservation and synchronization. Human evaluations further confirm its superiority, achieving higher synchronization and visual naturalness scores compared to the leading methods. These results demonstrate that our content-aware editing approach outperforms traditional generation or inpainting, particularly in maintaining complex visual elements while ensuring accurate lip synchronization.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video Editing for Audio-Visual Dubbing
Manela, Binyamin
Gannot, Sharon
Fetyaya, Ethan
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Visual dubbing, the synchronization of facial movements with new speech, is crucial for making content accessible across different languages, enabling broader global reach. However, current methods face significant limitations. Existing approaches often generate talking faces, hindering seamless integration into original scenes, or employ inpainting techniques that discard vital visual information like partial occlusions and lighting variations. This work introduces EdiDub, a novel framework that reformulates visual dubbing as a content-aware editing task. EdiDub preserves the original video context by utilizing a specialized conditioning scheme to ensure faithful and accurate modifications rather than mere copying. On multiple benchmarks, including a challenging occluded-lip dataset, EdiDub significantly improves identity preservation and synchronization. Human evaluations further confirm its superiority, achieving higher synchronization and visual naturalness scores compared to the leading methods. These results demonstrate that our content-aware editing approach outperforms traditional generation or inpainting, particularly in maintaining complex visual elements while ensuring accurate lip synchronization.
title Video Editing for Audio-Visual Dubbing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.23406