面向基于扩散的视频编辑的中性编辑框架
Neutral Editing Framework for Diffusion-based Video Editing
AI总结：
本文提出 NeuEdit 框架，通过“中性化”机制以模型无关方式增强扩散视频编辑流程，仅依赖视频和文本即可实现此前未被探索的人物/对象运动级复杂非刚性编辑。
摘要：
文本条件图像编辑已在基于扩散框架的各类编辑中取得成功。遗憾的是，这一成功并未延续到视频领域，视频编辑仍具挑战性。现有视频编辑系统仍局限于风格迁移和对象叠加等刚性类型编辑。为此，本文提出 Neutral Editing（NeuEdit，中性编辑）框架，通过改变视频中人物/对象的运动来实现复杂的非刚性编辑，这是此前从未尝试过的。NeuEdit 引入“中性化”概念，以模型无关的方式增强基于扩散的编辑系统的调优-编辑过程，仅利用输入视频和文本，无需任何其他辅助手段（例如视觉掩码、视频字幕）。在大量视频上进行的广泛实验证明了 NeuEdit 框架的适应性和有效性。本工作的网站可在此访问：https://neuedit.github.io
英文摘要：
Text-conditioned image editing has succeeded in various types of editing based on a diffusion framework. Unfortunately, this success did not carry over to a video, which continues to be challenging. Existing video editing systems are still limited to rigid-type editing such as style transfer and object overlay. To this end, this paper proposes Neutral Editing (NeuEdit) framework to enable complex non-rigid editing by changing the motion of a person/object in a video, which has never been attempted before. NeuEdit introduces a concept of `neutralization' that enhances a tuning-editing process of diffusion-based editing systems in a model-agnostic manner by leveraging input video and text without any other auxiliary aids (e.g., visual masks, video captions). Extensive experiments on numerous videos demonstrate adaptability and effectiveness of the NeuEdit framework. The website of our work is available here: https://neuedit.github.io
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。
