EVA：零样本精确属性与多对象视频编辑
EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing
AI总结：
提出零样本多属性视频编辑框架EVA，通过时空布局引导注意力机制和离散文本嵌入解决注意力泄漏问题，实现精确的前景背景同时编辑及多对象身份映射。
摘要：
当前基于扩散模型的视频编辑主要利用各种密集对应关系进行局部编辑（例如，对象/背景编辑）或全局风格编辑。然而，这些方法往往无法在保留原始布局的同时准确地同时编辑前景和背景。我们发现问题的症结在于指定区域内注意力权重分布不精确，包括不准确的文本到属性控制和注意力泄漏。为了解决这个问题，我们引入了EVA，这是一个专为具有复杂运动的以人为中心的视频量身定制的零样本和多属性视频编辑框架。我们结合了一种时空布局引导注意力机制，利用跨帧扩散特征的内在正负对应关系。为了避免注意力泄漏，我们利用这些对应关系来提升所有视频帧中同一属性内token的注意力分数，同时限制自注意力层中不同属性token之间的交互。为了实现精确的文本到属性操作，我们使用集中于交叉注意力层内特定布局区域的离散文本嵌入。得益于精确的注意力权重分布，EVA可以轻松推广到多对象编辑场景，并实现精确的身份映射。大量实验表明，EVA在真实场景中取得了最先进的结果。完整结果提供于 https://knightyxp.github.io/EVA/
英文摘要：
Current diffusion-based video editing primarily focuses on local editing (\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the foreground and background simultaneously while preserving the original layout. We find that the crux of the issue stems from the imprecise distribution of attention weights across designated regions, including inaccurate text-to-attribute control and attention leakage. To tackle this issue, we introduce EVA, a \textbf{zero-shot} and \textbf{multi-attribute} video editing framework tailored for human-centric videos with complex motions. We incorporate a Spatial-Temporal Layout-Guided Attention mechanism that leverages the intrinsic positive and negative correspondences of cross-frame diffusion features. To avoid attention leakage, we utilize these correspondences to boost the attention scores of tokens within the same attribute across all video frames while limiting interactions between tokens of different attributes in the self-attention layer. For precise text-to-attribute manipulation, we use discrete text embeddings focused on specific layout areas within the cross-attention layer. Benefiting from the precise attention weight distribution, EVA can be easily generalized to multi-object editing scenarios and achieves accurate identity mapping. Extensive experiments demonstrate EVA achieves state-of-the-art results in real-world scenarios. Full results are provided at https://knightyxp.github.io/EVA/
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。
