UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing
It addresses video editing challenges for AI and multimedia applications, offering a unified solution for motion and appearance changes, but it appears incremental as it builds on existing inversion-then-generation frameworks.
The paper tackles the problem of video motion editing, which is underexplored compared to appearance editing, by proposing UniEdit, a tuning-free framework that supports both motion and appearance editing using a pre-trained text-to-video generator, and it surpasses state-of-the-art methods in experiments.
Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.g., from eating to waving), which distinguishes video editing from image editing, is underexplored. In this work, we present UniEdit, a tuning-free framework that supports both video motion and appearance editing by harnessing the power of a pre-trained text-to-video generator within an inversion-then-generation framework. To realize motion editing while preserving source video content, based on the insights that temporal and spatial self-attention layers encode inter-frame and intra-frame dependency respectively, we introduce auxiliary motion-reference and reconstruction branches to produce text-guided motion and source features respectively. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers. Extensive experiments demonstrate that UniEdit covers video motion editing and various appearance editing scenarios, and surpasses the state-of-the-art methods. Our code will be publicly available.