跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 21 天前AI 評分43

MoviEdit:輕鬆編輯長篇多鏡頭影片

MoviEdit: Long-form Multi-Shot Video Editing Made Easy

AI 導讀

MoviEdit 是一個端到端長篇多鏡頭影片編輯框架,透過級聯式雙向自回歸建模,在跨場景轉換時維持影片連貫性。研究團隊建立自動資料生成流程,產出 87K 組無需人工標註的配對編輯影片,並推出 MoviEdit-Bench 作系統化評估。實驗顯示,MoviEdit 大幅超越現有開源模型,在文字引導及圖片引導編輯方面的表現媲美業界前沿模型。

正文

Abstract

MoviEdit is an end-to-end framework for long-form multi-shot video editing that uses cascaded bidirectional-autoregressive modeling and a new benchmark to maintain coherence across scenes while reducing manual data annotation.

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. To provide cross-shot supervision data at scale, we develop automatic data-generation pipelines spanning synchronized multi-view footage, real-world multi-shot videos, and generated multi-shot content, yielding 87K paired editing videos without manual annotation. Architecturally, MoviEdit employs a cascaded bidirectional-autoregressive design: a lightweight bidirectional stage first establishes a globally coherent editing draft over a spatiotemporally compressed representation, which is then autoregressively propagated and refined over the full video. We further introduce MoviEdit-Bench, a dedicated benchmark for systematic evaluation of long-form multi-shot video editing. Extensive experiments show that MoviEdit substantially outperforms existing open-source models and performs on par with industry frontier models across text-guided and image-guided editing. Visit our project page for complete results and to access the benchmark: https://multi-shot-edit.github.io/

View arXiv page View PDF Project page GitHub Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.02737 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.02737 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.02737 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co