Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner
Haojie Zheng, Shuchen Weng, Jingqi Liu, Siqi Yang, Boxin Shi, Xinlong Wang
Abstract
Recent advancements in video generation highlight that realistic audio-visual synchronization is crucial for engaging content creation. However, existing video editing methods largely overlook audio-visual synchronization and lack the fine-grained spatial and temporal controllability required for precise instance-level edits. In this paper, we propose AVI-Edit, a framework for audio-sync video instance editing. We propose a granularity-aware mask refiner that iteratively refines coarse user-provided masks into precise instance-level regions. We further design a self-feedback audio agent to curate high-quality audio guidance, providing fine-grained temporal control. To facilitate this task, we additionally construct a large-scale dataset with instance-centric correspondence and comprehensive annotations. Extensive experiments demonstrate that AVI-Edit outperforms state-of-the-art methods in visual quality, condition following, and audio-visual synchronization. Project page: https://hjzheng.net/projects/AVI-Edit/.
BibTeX
@inproceedings{cvpr2026_audiosyncvideoin,
title = {Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner},
author = {Haojie Zheng and Shuchen Weng and Jingqi Liu and Siqi Yang and Boxin Shi and Xinlong Wang},
booktitle = {CVPR 2026},
year = {2026}
}