We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative inpainting, to modify the first frame; it automatically propagates those changes, with semantic, spatial, and temporally consistent motion, to the remaining frames. Unlike existing methods that enable edits only through imprecise textual instructions, Videoshop allows users to add or remove objects, semantically change objects, insert stock photos into videos, etc. with fine-grained control over locations and appearance. We achieve this through image-based video editing by inverting latents with noise extrapolation, from which we generate videos conditioned on the edited image. Videoshop produces higher quality edits against 6 baselines on 2 editing benchmarks using 10 evaluation metrics.

我们介绍了Videoshop，这是一种针对局部语义编辑的无需训练的视频编辑算法。Videoshop允许用户使用任何编辑软件，包括Photoshop和生成修饰，来修改第一帧，并自动将这些变化以语义、空间和时间一致的动作传播到其余的帧。与现有的仅通过不精确的文本指令进行编辑的方法不同，Videoshop允许用户添加或删除对象、在视频中进行语义变更、插入股票照片等，并对位置和外观进行精细控制。我们通过基于图像的视频编辑，并通过对编辑图像的噪声推断反演来生成视频，实现了这一目标。在2个编辑基准测试中，通过使用10个评估指标，Videoshop相对于6个基线方法获得更高质量的编辑结果。

Videoshop：具有噪声外推扩散反演的本地化语义视频编辑