V2Edit：面向视频与3D场景的通用视频扩散编辑器
V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes
AI总结：
提出无需训练的 V$^2$Edit 框架，通过渐进任务分解与噪声、交叉注意力控制实现视频编辑，并以“渲染-编辑-重建”扩展至高质量3D一致场景编辑。
摘要：
本文介绍了 V$^2$Edit，这是一种新颖的、无需训练的框架，用于指令引导的视频和3D场景编辑。为解决在保留原始内容与完成编辑任务之间取得平衡这一关键挑战，我们的方法采用渐进式策略，将复杂编辑任务分解为一系列更简单的子任务。每个子任务通过三个关键的协同机制进行控制：初始噪声、每个去噪步骤添加的噪声，以及文本提示与视频内容之间的交叉注意力图。这确保了在有效应用所需编辑的同时，稳健保留原始视频元素。除其原生视频编辑能力外，我们还通过“渲染-编辑-重建”流程将 V$^2$Edit 扩展到3D场景编辑，即使对于涉及显著几何变化的任务（如物体插入），也能实现高质量、3D一致的编辑。大量实验表明，我们的 V$^2$Edit 在各种具有挑战性的视频编辑任务和复杂的3D场景编辑任务中均实现了高质量且成功的编辑，从而在两个领域都确立了最先进的性能。
英文摘要：
This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach employs a progressive strategy that decomposes complex editing tasks into a sequence of simpler subtasks. Each subtask is controlled through three key synergistic mechanisms: the initial noise, noise added at each denoising step, and cross-attention maps between text prompts and video content. This ensures robust preservation of original video elements while effectively applying the desired edits. Beyond its native video editing capability, we extend V$^2$Edit to 3D scene editing via a "render-edit-reconstruct" process, enabling high-quality, 3D-consistent edits even for tasks involving substantial geometric changes such as object insertion. Extensive experiments demonstrate that our V$^2$Edit achieves high-quality and successful edits across various challenging video editing tasks and complex 3D scene editing tasks, thereby establishing state-of-the-art performance in both domains.
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。
