MAG-Edit：基于掩码注意力调整引导的复杂场景局部图像编辑
MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance
AI总结：
MAG-Edit提出一种无需训练、推理阶段优化的方法，通过最大化掩码交叉注意力约束，实现复杂场景下的局部图像编辑，兼顾文本对齐与结构保留。
摘要：
近期基于扩散模型的图像编辑方法在简单构图图像上展现了令人印象深刻的编辑能力。然而，尽管现实需求日益增长，文献中对复杂场景下的局部编辑研究仍不充分。现有的基于掩码的修复方法在保留编辑区域内部底层结构方面存在不足。同时，无掩码的基于注意力的方法在更复杂的构图中常常出现编辑泄漏和错位问题。在本工作中，我们开发了MAG-Edit，一种无需训练、推理阶段优化的方法，能够在复杂场景中实现局部图像编辑。具体而言，MAG-Edit通过最大化编辑标记的两个基于掩码的交叉注意力约束来优化扩散模型中的噪声潜在特征，从而逐步增强与期望提示的局部对齐。大量的定量和定性实验证明了我们的方法在复杂场景局部编辑中实现文本对齐和结构保留的有效性。
英文摘要：
Recent diffusion-based image editing approaches have exhibited impressive editing capabilities in images with simple compositions. However, localized editing in complex scenarios has not been well-studied in the literature, despite its growing real-world demands. Existing mask-based inpainting methods fall short of retaining the underlying structure within the edit region. Meanwhile, mask-free attention-based methods often exhibit editing leakage and misalignment in more complex compositions. In this work, we develop MAG-Edit, a training-free, inference-stage optimization method, which enables localized image editing in complex scenarios. In particular, MAG-Edit optimizes the noise latent feature in diffusion models by maximizing two mask-based cross-attention constraints of the edit token, which in turn gradually enhances the local alignment with the desired prompt. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in achieving both text alignment and structure preservation for localized editing within complex scenarios.
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。
