只改需要动的区域，让图像编辑更快更准。
SpotEdit: Selective Region Editing in Diffusion Transformers
- 按视觉相似性识别稳定区域，跳过无意义计算。
- 动态融合机制确保未修改区域保持高质量。
- 无需训练，可直接用于现有扩散模型。
扩散变压器模型通过编码条件图像并将其融入变换器层，显著推动了图像编辑的发展。然而，大多数编辑仅涉及小范围区域，而现有方法在每个时间步均对所有标记进行统一处理和去噪，导致冗余计算，并可能损害未修改区域的质量。这引发一个根本问题：编辑时是否真需重生成每个区域？为此，我们提出 SpotEdit——一种无需训练的扩散编辑框架，仅选择性更新被修改的区域。SpotEdit 包含两个核心组件：SpotSelector 通过感知相似性识别稳定区域，通过复用条件图像特征跳过计算；SpotFusion 通过动态融合机制将这些特征与已编辑标记相结合，保持上下文连贯性和编辑质量。通过减少不必要的计算并维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。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。