SpotEdit: 差分变换器中的选择性区域编辑
SpotEdit: Selective Region Editing in Diffusion Transformers
AI总结：
SpotEdit提出了一种无需训练的差分编辑框架，通过选择性更新修改区域，实现高效且精确的图像编辑。
摘要：
差分变换器模型通过编码条件图像并将它们整合到变换器层中，显著提高了图像编辑的水平。然而，大多数编辑仅涉及修改小区域，而当前方法在每个时间步都统一处理和去噪所有标记，导致冗余计算并可能降质未修改的区域。这引发了一个根本性问题：在编辑过程中是否真的需要重新生成每个区域？为此，我们提出了SpotEdit，一种无需训练的差分编辑框架，仅选择性地更新修改区域。SpotEdit包含两个关键组件：SpotSelector通过感知相似性识别稳定区域并通过重用条件图像特征跳过其计算；SpotFusion通过动态融合机制适应性地将这些特征与编辑标记融合，保持上下文一致性和编辑质量。通过减少不必要的计算并保持未修改区域的高保真度，SpotEdit实现了高效且精确的图像编辑。
英文摘要：
Diffusion Transformer models have significantly advanced image editing by encoding conditional images and integrating them into transformer layers. However, most edits involve modifying only small regions, while current methods uniformly process and denoise all tokens at every timestep, causing redundant computation and potentially degrading unchanged areas. This raises a fundamental question: Is it truly necessary to regenerate every region during editing? To address this, we propose SpotEdit, a training-free diffusion editing framework that selectively updates only the modified regions. SpotEdit comprises two key components: SpotSelector identifies stable regions via perceptual similarity and skips their computation by reusing conditional image features; SpotFusion adaptively blends these features with edited tokens through a dynamic fusion mechanism, preserving contextual coherence and editing quality. By reducing unnecessary computation and maintaining high fidelity in unmodified areas, SpotEdit achieves efficient and precise image editing.
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。
