CARE-Edit：面向上下文图像编辑的条件感知专家路由
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
用轻量潜变量注意力路由器按多模态条件与扩散时间步把 token 稀疏路由到 Text/Mask/Reference/Base 四个专家，可直接迁移到任何多条件 ControlNet 式编辑器中以缓解条件冲突与颜色渗漏。
原文依据 a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论统一扩散编辑器通常依赖固定的共享骨干网络来处理多样任务，因而受到任务干扰，并且难以适应异构需求（例如局部与全局、语义与光度）。尤其是常见的 ControlNet 与 OmniControl 变体通过静态拼接或加性适配器组合多种条件信号（如文本、掩码、参考图），无法动态地优先考虑或抑制相互冲突的模态，从而导致掩码边界处的颜色渗漏、身份或风格漂移，以及多条件输入下不可预测的行为。为解决这一问题，我们提出条件感知专家路由（CARE-Edit），使模型计算与特定编辑能力对齐。其核心是一个轻量的潜变量注意力路由器，它根据多模态条件与扩散时间步，将编码后的扩散 token 分配给四个专门专家——文本、掩码、参考与基础：(i) 掩码重绘模块首先细化粗略的用户定义掩码，以提供精确的空间引导；(ii) 路由器采用稀疏 top-K 选择，将计算动态分配给最相关的专家；(iii) 潜变量混合模块随后融合各专家输出，将语义、空间与风格信息连贯地整合到基础图像上。实验验证了 CARE-Edit 在上下文编辑任务上的强劲性能，包括擦除、替换、文本驱动编辑与风格迁移。实证分析进一步揭示了专门专家的任务特定行为，展示了动态、条件感知处理对于缓解多条件冲突的重要性。源代码、模型与数据集将公开可用。
英文原文摘要 1721 字符
Unified diffusion editors often rely on a fixed, shared backbone for diverse tasks, suffering from task interference and poor adaptation to heterogeneous demands (e.g., local vs global, semantic vs photometric). In particular, prevalent ControlNet and OmniControl variants combine multiple conditioning signals (e.g., text, mask, reference) via static concatenation or additive adapters which cannot dynamically prioritize or suppress conflicting modalities, thus resulting in artifacts like color bleeding across mask boundaries, identity or style drift, and unpredictable behavior under multi-condition inputs. To address this, we propose Condition-Aware Routing of Experts (CARE-Edit) that aligns model computation with specific editing competencies. At its core, a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts--Text, Mask, Reference, and Base--based on multi-modal conditions and diffusion timesteps: (i) a Mask Repaint module first refines coarse user-defined masks for precise spatial guidance; (ii) the router applies sparse top-K selection to dynamically allocate computation to the most relevant experts; (iii) a Latent Mixture module subsequently fuses expert outputs, coherently integrating semantic, spatial, and stylistic information to the base images. Experiments validate CARE-Edit's strong performance on contextual editing tasks, including erasure, replacement, text-driven edits, and style transfer. Empirical analysis further reveals task-specific behavior of specialized experts, showcasing the importance of dynamic, condition-aware processing to mitigate multi-condition conflicts. The source code, models, and dataset will be publicly available.