DNI：用于扩散视频编辑的稀释噪声初始化
DNI: Dilutional Noise Initialization for Diffusion Video Editing
AI总结：
本文提出稀释噪声初始化（DNI）框架，通过向待编辑区域的潜在噪声添加额外噪声以软化结构刚性，实现扩散视频编辑中的非刚性编辑，如运动变化，实验证明其有效性。
摘要：
基于文本的扩散视频编辑系统在实现高保真度和文本对齐的编辑方面已取得成功。然而，这种成功仅限于刚性编辑，如风格迁移和对象叠加，同时保持输入视频的原始结构。这一限制源于扩散视频编辑系统中使用的初始潜在噪声。扩散视频编辑系统通过逐步将高斯噪声注入输入视频来准备用于编辑的初始潜在噪声。然而，我们观察到输入视频的视觉结构仍然存在于该初始潜在噪声中，从而限制了需要结构修改的非刚性编辑，如运动变化。为此，本文提出了稀释噪声初始化（DNI）框架，使编辑系统能够执行精确和动态的修改，包括非刚性编辑。DNI引入了“噪声稀释”的概念，即在待编辑区域向潜在噪声添加更多噪声，以软化输入视频所施加的结构刚性，从而实现更接近目标提示的有效编辑。大量实验证明了DNI框架的有效性。
英文摘要：
Text-based diffusion video editing systems have been successful in performing edits with high fidelity and textual alignment. However, this success is limited to rigid-type editing such as style transfer and object overlay, while preserving the original structure of the input video. This limitation stems from an initial latent noise employed in diffusion video editing systems. The diffusion video editing systems prepare initial latent noise to edit by gradually infusing Gaussian noise onto the input video. However, we observed that the visual structure of the input video still persists within this initial latent noise, thereby restricting non-rigid editing such as motion change necessitating structural modifications. To this end, this paper proposes Dilutional Noise Initialization (DNI) framework which enables editing systems to perform precise and dynamic modification including non-rigid editing. DNI introduces a concept of `noise dilution' which adds further noise to the latent noise in the region to be edited to soften the structural rigidity imposed by input video, resulting in more effective edits closer to the target prompt. Extensive experiments demonstrate the effectiveness of the DNI framework.
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。
