解耦引导：文本到图像个性化中的主体与上下文路径分离
Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization
AI总结：
提出解耦引导（DeGu）框架，通过独立引导流分别处理主体身份和场景上下文，并引入空间混合机制动态融合，以解决个性化生成中保真度与可编辑性的权衡问题。
摘要：
文本到图像个性化旨在根据文本描述在 novel 场景中生成用户提供的主体。然而，大多数现有方法通过相同的条件路径编码主体身份（保真度）和上下文（可编辑性），迫使两者竞争注意力图资源。我们将这种现象称为条件纠缠，并表明它导致了保真度-可编辑性的权衡。我们进一步通过将目标主体 token 替换为通用主体 token 提供因果证据，这产生了注意力分配的转移以及上下文遵循度的相应变化。为此，我们提出解耦引导（DeGu），一个即插即用框架，通过两个独立的引导流路由主体身份和场景上下文。我们进一步引入空间混合机制，动态融合这些流，确保每个流在其语义相关区域内运行而不受干扰。此外，DeGu 可以轻松应用于现有个性化方法，无需修改底层骨干模型，一致地提升整体个性化性能，同时实现对保真度-可编辑性平衡的推理时控制，适用于多种方法和骨干网络，包括流匹配扩散变换器（DiTs）。
英文摘要：
Text-to-image personalization aims to generate a user-provided subject in novel scenes described by text. However, most existing methods encode subject identity (fidelity) and context (editability) through the same conditioning pathway, forcing the two to compete for attention-map resources. We refer to this phenomenon as conditioning entanglement and show that it induces a fidelity-editability trade-off. We further provide causal evidence by replacing the target subject token with a generic subject token, which produces shifts in attention allocation and corresponding changes in context adherence. To this end, we propose Decoupled Guidance (DeGu), a plug-and-play framework that routes subject identity and scene context through two independent guidance streams. We further introduce a spatial mixing mechanism that dynamically fuses these streams, ensuring each operates within its semantically relevant region without interference. Furthermore, DeGu can be readily applied to existing personalization methods without modifying the underlying backbone models, consistently improving the overall personalization performance while enabling inference-time control over the fidelity-editability balance, across diverse methods and backbones, including flow-matching Diffusion Transformers (DiTs).
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。
