InstructVEdit: A Holistic Approach for Instructional Video Editing
This work solves the problem of editing videos based on instructions for users in video production, but it is incremental as it builds on prior improvements in specific aspects.
The paper tackles the challenge of instructional video editing by introducing InstructVEdit, a holistic framework that addresses data scarcity and model design, achieving state-of-the-art performance with robust adaptability in diverse real-world scenarios.
Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the systematic exploration of model architectures and training strategies. While prior work has improved specific aspects of video editing (e.g., synthesizing a video dataset using image editing techniques or decomposed video editing training), a holistic framework addressing the above challenges remains underexplored. In this study, we introduce InstructVEdit, a full-cycle instructional video editing approach that: (1) establishes a reliable dataset curation workflow to initialize training, (2) incorporates two model architectural improvements to enhance edit quality while preserving temporal consistency, and (3) proposes an iterative refinement strategy leveraging real-world data to enhance generalization and minimize train-test discrepancies. Extensive experiments show that InstructVEdit achieves state-of-the-art performance in instruction-based video editing, demonstrating robust adaptability to diverse real-world scenarios. Project page: https://o937-blip.github.io/InstructVEdit.