SpotEdit：扩散 Transformer 中的选择性区域编辑
SpotEdit: Selective Region Editing in Diffusion Transformers
SpotSelector 用感知相似度判定哪些 token 在编辑中保持稳定并直接复用条件图像特征，SpotFusion 再做动态融合——这套「只去噪变化区域」的免训练策略可直接移植到任何 DiT 类编辑/修复管线，用来省算力并避免未编辑区域被破坏。
原文依据 a training-free diffusion editing framework that selectively updates only the modified regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于扩散 Transformer（DiT）的模型通过编码条件图像并将其整合进 Transformer 层，显著推动了图像编辑的发展。然而，大多数编辑只涉及对较小区域的修改，而现有方法在每个时间步都统一处理并对全部 token 去噪，造成冗余计算，并可能使未改动区域退化。这引出一个根本性问题：编辑时是否真的有必要重新生成每一个区域？为此，我们提出 SpotEdit，一个免训练的扩散编辑框架，仅对发生修改的区域进行选择性更新。SpotEdit 包含两个关键组件：SpotSelector 通过感知相似度识别稳定区域，并复用条件图像特征以跳过其计算；SpotFusion 通过动态融合机制将这些特征与编辑后的 token 自适应地混合，从而保持上下文连贯性与编辑质量。通过减少不必要的计算并在未修改区域保持高保真度，SpotEdit 实现了高效且精确的图像编辑。
英文原文摘要 1072 字符
Diffusion Transformer (DiT)-based 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.