为文本引导的图像生成注入多轮思维
Instilling Multi-round Thinking to Text-guided Image Generation
AI总结：
针对文本引导图像编辑中单轮生成易忽略细粒度细节、多轮交互误差累积的问题，提出兼容现有方法的多轮正则化自监督策略，通过约束修改顺序一致性放大初始细节误差，实现单/多轮高保真编辑，且泛化性和语义对齐效果优异。
摘要：
本文深入研究文本引导的图像编辑任务，重点是根据用户指定的文本反馈修改参考图像，使其呈现特定属性。尽管近期取得了进展，但一个持续存在的挑战是单轮生成往往会忽略关键细节，尤其是在鞋子或袖子等细粒度变化方面。这个问题在多轮交互中会不断加剧，严重限制定制质量。为了应对这一挑战，我们提出了一种新的自监督正则化方法，即多轮正则化，它与现有方法兼容。具体而言，多轮正则化促使模型在不同的修改顺序之间保持一致性，它基于这样的观察：修改顺序通常不应影响最终结果。与传统的单轮生成不同，所提方法的核心机制是对捕捉复杂细节时最初的微小不准确性进行误差放大。定性和定量实验证实，所提方法在单轮和多轮生成中都实现了高保真的编辑质量，尤其是局部修改，同时还展现出对不规则文本输入的强泛化能力。我们与文本反馈的语义对齐的有效性通过在FahisonIQ和Fashion200k上的检索性能提升得到了进一步证实。
英文摘要：
This paper delves into the text-guided image editing task, focusing on modifying a reference image according to user-specified textual feedback to embody specific attributes. Despite recent advancements, a persistent challenge remains that the single-round generation often overlooks crucial details, particularly in the realm of fine-grained changes like shoes or sleeves. This issue compounds over multiple rounds of interaction, severely limiting customization quality. In an attempt to address this challenge, we introduce a new self-supervised regularization, \ie, multi-round regularization, which is compatible with existing methods. Specifically, the multi-round regularization encourages the model to maintain consistency across different modification orders. It builds upon the observation that the modification order generally should not affect the final result. Different from traditional one-round generation, the mechanism underpinning the proposed method is the error amplification of initially minor inaccuracies in capturing intricate details. Qualitative and quantitative experiments affirm that the proposed method achieves high-fidelity editing quality, especially the local modification, in both single-round and multiple-round generation, while also showcasing robust generalization to irregular text inputs. The effectiveness of our semantic alignment with textual feedback is further substantiated by the retrieval improvements on FahisonIQ and Fashion200k.
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。
