FlexiEdit：用于增强非刚性编辑的频率感知潜变量细化
FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing
AI总结：
针对DDIM Inversion在非刚性图像编辑中的局限，FlexiEdit通过细化DDIM潜变量以减少目标区域高频分量，并结合重反转增强编辑保真度，显著提升了复杂非刚性编辑能力。
摘要：
当前图像编辑方法主要利用DDIM Inversion，采用双分支扩散方法来保留原始图像的属性和布局。然而，这些方法在处理非刚性编辑时遇到挑战，非刚性编辑涉及改变图像的布局或结构。我们的综合分析表明，DDIM潜变量的高频分量对保留原始图像的关键特征和布局至关重要，它们对这些局限性有显著影响。针对此问题，我们引入FlexiEdit，通过细化DDIM潜变量、减少目标编辑区域的高频分量，增强对输入文本提示的保真度。FlexiEdit包含两个关键组件：(1)潜变量细化，修改DDIM潜变量以更好地适应布局调整；(2)通过重反转增强编辑保真度，旨在确保编辑更准确地反映输入文本提示。我们的方法在图像编辑领域取得显著进展，特别是在执行复杂非刚性编辑方面，通过对比实验展示了其增强的能力。
英文摘要：
Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image. However, these methods encounter challenges with non-rigid edits, which involve altering the image's layout or structure. Our comprehensive analysis reveals that the high-frequency components of DDIM latent, crucial for retaining the original image's key features and layout, significantly contribute to these limitations. Addressing this, we introduce FlexiEdit, which enhances fidelity to input text prompts by refining DDIM latent, by reducing high-frequency components in targeted editing areas. FlexiEdit comprises two key components: (1) Latent Refinement, which modifies DDIM latent to better accommodate layout adjustments, and (2) Edit Fidelity Enhancement via Re-inversion, aimed at ensuring the edits more accurately reflect the input text prompts. Our approach represents notable progress in image editing, particularly in performing complex non-rigid edits, showcasing its enhanced capability through comparative experiments.
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。
