MoviEdit enables long-form multi-shot video editing
Original title: MoviEdit: Long-form Multi-Shot Video Editing Made Easy
MoviEdit uses cascaded bidirectional-autoregressive design and 87K training videos to outperform open-source models on video editing.
MoviEdit is an end-to-end framework for scalable long-form multi-shot video editing that jointly addresses data, modeling, and evaluation challenges. Automatic data-generation pipelines spanning synchronized multi-view footage, real-world multi-shot videos, and generated content yield 87K paired editing videos without manual annotation. A cascaded bidirectional-autoregressive design first establishes a globally coherent editing draft over a spatiotemporally compressed representation, then refines it autoregressively over the full video. Extensive experiments show MoviEdit outperforms existing open-source models and performs on par with industry frontier models across text-guided and image-guided editing.
- 87K paired editing videos from automatic pipelines
- Cascaded bidirectional-autoregressive design
- MoviEdit-Bench dedicated evaluation benchmark
- Outperforms open-source models
- Matches industry frontier models
From the original article
1 min read at huggingface.co
Long-form multi-shot video editing requires an intended edit to remain coherent across abrupt changes in scene, viewpoint, and subject appearance, while processing substantially longer visual context than conventional single-shot editors. We introduce MoviEdit, an end-to-end framework for scalable long-form multi-shot video editing that jointly addresses the challenges of data, modeling, and evaluation.
By Suhyeon Lee, Zhengang Li, Soo Ye Kim · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.