CARE-Edit：基于条件的专家路由用于上下文图像编辑
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
AI总结：
CARE-Edit通过条件感知的专家路由提升上下文图像编辑的性能和稳定性
摘要：
统一的扩散编辑器通常依赖于一个固定、共享的骨干网络来处理多种任务，导致任务干扰和对异构需求的适应性差（例如局部 vs 全局，语义 vs 光度）。特别是，流行的ControlNet和OmniControl变体通过静态拼接或加法适配器将多种条件信号（例如文本、掩码、参考）结合起来，无法动态优先或抑制冲突的模态，从而导致诸如掩码边界处的颜色溢出、身份或风格漂移以及多条件输入下的不可预测行为。为了解决这一问题，我们提出了条件感知的专家路由（CARE-Edit），使模型计算与特定的编辑能力对齐。其核心是一个轻量级的潜在注意力路由器，根据多模态条件和扩散时间步将编码的扩散令牌分配给四个专门的专家——文本、掩码、参考和基础——：（i）掩码重绘模块首先细化用户定义的粗略掩码，以提供精确的空间指导；（ii）路由器应用稀疏top-K选择，动态地将计算分配给最相关的专家；（iii）潜在混合模块随后融合专家输出，相干地将语义、空间和风格信息整合到基础图像中。实验验证了CARE-Edit在上下文编辑任务中的强大性能，包括擦除、替换、文本驱动编辑和风格迁移。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、条件感知处理在缓解多条件冲突中的重要性。
英文摘要：
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.
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。
