解耦以再耦合：在主体驱动的文本到图像生成中解决相似性-可控性悖论
Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation
AI总结：
本文提出DisCo框架，通过解耦和再耦合视觉与文本信息，解决主体驱动文本到图像生成中相似性与可控性矛盾问题，实现高保真主体保持与精确文本控制。
摘要：
主体驱动的文本到图像（T2I）生成旨在基于文本提示在保持主体身份的同时编辑其上下文。该任务的核心挑战是'相似性-可控性悖论'，即增强文本控制通常会降低主体的保真度，反之亦然。我们认为这一悖论源于文本提示的模糊角色，它们通常被要求同时描述主体和期望的修改，导致模型接收到冲突的信号。为了解决这一问题，我们提出了DisCo，一种新的框架，首先解耦然后重新耦合视觉和文本信息。首先，我们的文本-视觉解耦模块隔离了信息来源：主体身份仅从参考图像中使用主体词提取，而文本提示被简化为仅包含修改命令，其中主体指代一般代词，消除描述模糊性。然而，这种严格分离可能导致主体与其上下文之间的不自然组合。我们通过设计专门的奖励信号并使用强化学习来无缝重新耦合视觉定义的主体和文本生成的上下文。我们的方法有效解决了这一悖论，使同时实现高保真的主体保持和精确的文本控制成为可能。广泛的实验表明，我们的方法在生成高度真实和连贯的图像方面取得了最先进的性能。
英文摘要：
Subject-Driven Text-to-Image (T2I) Generation aims to preserve a subject's identity while editing its context based on a text prompt. A core challenge in this task is the "similarity-controllability paradox", where enhancing textual control often degrades the subject's fidelity, and vice-versa. We argue this paradox stems from the ambiguous role of text prompts, which are often tasked with describing both the subject and the desired modifications, leading to conflicting signals for the model. To resolve this, we propose DisCo, a novel framework that first Disntangles and then re-Couples visual and textual information. First, our textual-visual decoupling module isolates the sources of information: subject identity is extracted exclusively from the reference image with the entity word of the subject, while the text prompt is simplified to contain only the modification command, where the subject refers to general pronouns, eliminating descriptive ambiguity. However, this strict separation can lead to unnatural compositions between the subject and its contexts. We address this by designing a dedicated reward signal and using reinforcement learning to seamlessly recouple the visually-defined subject and the textually-generated context. Our approach effectively resolves the paradox, enabling simultaneous high-fidelity subject preservation and precise textual control. Extensive experiments demonstrate that our method achieves state-of-the-art performance, producing highly realistic and coherent images.
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。
