在需要的地方编辑：区域感知的适配器注入用于无掩码的局部图像编辑
Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing
AI总结：
本文提出AdaptEdit框架，通过区域感知适配器实现无掩码的局部图像编辑，结合轻量级Block Adapter和SpatialGate提升编辑精度，同时通过Region-Aware Loss优化训练目标，实现无需用户掩码的高质量编辑。
摘要：
大型扩散变换器（DiTs）在遵循全局编辑指令方面表现良好，但会将局部编辑泄露到无关区域，因为联合注意力架构无法明确指示网络应用编辑的位置。我们引入AdaptEdit，一种联合训练、指令和区域感知的适配器框架，将冻结的DiT精确转换为局部编辑器，而无需修改其主干权重。每个Transformer块中的轻量级Block Adapter注入结构化的条件流，将要编辑的内容（指令语义）与要编辑的位置（空间掩码）分离；学习的SpatialGate将适配器信号选择性地路由到编辑区域，同时保持图像其余部分与源图像几乎相同；Region-Aware Loss将训练目标聚焦于变化的像素。由于这些组件使主干的内部表示成为mask-aware end-to-end，一个与编辑器联合训练的薄MaskPredictor头可以直接从指令和源图像中确定编辑区域--消除了部署时任何用户掩码的需求。我们在两个互补的基准上进行了评估：MagicBrush（配对的真实目标）以测量像素级的保持和编辑准确性，以及Emu-Edit Test（无真实图像，9种不同的编辑类别）以压力测试指令跟随和跨编辑类型的泛化能力。在两者上，AdaptEdit均取得最佳结果，同时优于无掩码和oracle-mask基线。七种变体的消融分析清晰地隔离了每个组件的贡献。
英文摘要：
Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no explicit channel telling the network where to apply the edit. We introduce AdaptEdit, a co-trained, instruction- and region-aware adapter framework that retro-fits a frozen DiT into a precise local editor without modifying its backbone weights. A lightweight Block Adapter at every transformer block injects a structured condition stream that factorizes what to edit (instruction semantics) from where to edit (spatial mask); a learned SpatialGate routes the adapter signal selectively into the edit region while keeping the rest of the image near-identical to the source; and a Region-Aware Loss focuses the training objective on the changing pixels. Because these components make the backbone's internal representation mask-aware end-to-end, a thin MaskPredictor head trained jointly with the editor can ground the edit region directly from the instruction and source image -- eliminating any user-mask requirement at deployment. We evaluate on two complementary benchmarks: MagicBrush (paired ground-truth targets) to measure pixel-level preservation and edit accuracy, and Emu-Edit Test (no ground-truth images, 9 diverse edit categories) to stress-test instruction following and generalization across edit types. On both, AdaptEdit achieves state-of-the-art results, simultaneously outperforming mask-free and oracle-mask baselines. A seven-variant ablation cleanly isolates the contribution of each component.
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。
