VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editing

TL;DR

VIA is a unified framework that enables consistent and precise global and local editing of long videos by adapting pre-trained models for spatiotemporal coherence and control.

Contribution

The paper introduces VIA, a novel spatiotemporal video adaptation framework that improves long video editing consistency and local control through test-time and recursive attention strategies.

Findings

Produces more faithful and coherent video edits

Achieves consistent long video editing in minutes

Outperforms baseline methods in accuracy and control

Abstract

Video editing serves as a fundamental pillar of digital media, spanning applications in entertainment, education, and professional communication. However, previous methods often overlook the necessity of comprehensively understanding both global and local contexts, leading to inaccurate and inconsistent edits in the spatiotemporal dimension, especially for long videos. In this paper, we introduce VIA, a unified spatiotemporal Video Adaptation framework for global and local video editing, pushing the limits of consistently editing minute-long videos. First, to ensure local consistency within individual frames, we designed test-time editing adaptation to adapt a pre-trained image editing model for improving consistency between potential editing directions and the text instruction, and adapts masked latent variables for precise local control. Furthermore, to maintain global consistency over the video sequence, we introduce spatiotemporal adaptation that recursively gather consistent attention variables in key frames and strategically applies them across the whole sequence to realize the editing effects. Extensive experiments demonstrate that, compared to baseline methods, our VIA approach produces edits that are more faithful to the source videos, more coherent in the spatiotemporal context, and more precise in local control. More importantly, we show that VIA can achieve consistent long video editing in minutes, unlocking the potential for advanced video editing tasks over long video sequences.