使用现成图像扩散模型的零样本视频编辑
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
AI总结:
提出vid2vid-zero零样本视频编辑方法,利用现成图像扩散模型,通过空文本反演、跨帧建模和空间正则化模块实现文本到视频对齐、时间一致性和保真度,无需训练即可在真实视频上取得良好编辑效果。
摘要:
大规模文本到图像扩散模型在图像生成和编辑方面取得了前所未有的成功。然而,如何将这种成功扩展到视频编辑尚不明确。最近在视频编辑方面的初步尝试需要大量的文本到视频数据和计算资源进行训练,这通常是难以获取的。在这项工作中,我们提出了vid2vid-zero,一种简单而有效的零样本视频编辑方法。我们的vid2vid-zero利用现成的图像扩散模型,不需要在任何视频上进行训练。我们方法的核心是一个用于文本到视频对齐的空文本反演模块,一个用于时间一致性的跨帧建模模块,以及一个用于保持对原始视频保真度的空间正则化模块。在无需任何训练的情况下,我们利用注意力机制的动态特性,在测试时实现双向时间建模。实验和分析表明,在真实世界视频中编辑属性、主体、地点等方面取得了有希望的结果。代码可在https://github.com/baaivision/vid2vid-zero获取。
英文摘要:
Large-scale text-to-image diffusion models achieve unprecedented success in image generation and editing. However, how to extend such success to video editing is unclear. Recent initial attempts at video editing require significant text-to-video data and computation resources for training, which is often not accessible. In this work, we propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Our vid2vid-zero leverages off-the-shelf image diffusion models, and doesn't require training on any video. At the core of our method is a null-text inversion module for text-to-video alignment, a cross-frame modeling module for temporal consistency, and a spatial regularization module for fidelity to the original video. Without any training, we leverage the dynamic nature of the attention mechanism to enable bi-directional temporal modeling at test time. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos. Code is made available at \url{https://github.com/baaivision/vid2vid-zero}.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。