UniEdit-Flow：在流模型时代释放反向与编辑
UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
AI总结：
本文提出了一种基于预测-校正框架的流模型反向与编辑方法，通过Uni-Inv实现准确重建，并通过Uni-Edit实现区域感知的图像编辑，方法无需调优，具有通用性和高效性，实验表明其在多种生成模型中均表现出色。
摘要：
流匹配模型已作为一种强大的替代扩散模型的选项，但现有的针对扩散模型的反向和编辑方法往往在流模型上效果不佳或不适用。流模型的直线、非交叉轨迹对基于扩散的方法构成了挑战，但也为新的解决方案提供了途径。在本文中，我们介绍了一种用于流模型反向和编辑的预测-校正框架。首先，我们提出了Uni-Inv，一种有效的反向方法，用于准确的重建。在此基础上，我们将延迟注入的概念扩展到流模型，并引入Uni-Edit，一种区域感知且稳健的图像编辑方法。我们的方法无需调优，模型无关，高效且有效，能够在多样化编辑的同时，确保对编辑无关区域的强保留。在各种生成模型上的广泛实验表明，Uni-Inv和Uni-Edit的优越性和通用性，即使在低成本设置下也是如此。项目页面：https://uniedit-flow.github.io/
英文摘要：
Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicable to them. The straight-line, non-crossing trajectories of flow models pose challenges for diffusion-based approaches but also open avenues for novel solutions. In this paper, we introduce a predictor-corrector-based framework for inversion and editing in flow models. First, we propose Uni-Inv, an effective inversion method designed for accurate reconstruction. Building on this, we extend the concept of delayed injection to flow models and introduce Uni-Edit, a region-aware, robust image editing approach. Our methodology is tuning-free, model-agnostic, efficient, and effective, enabling diverse edits while ensuring strong preservation of edit-irrelevant regions. Extensive experiments across various generative models demonstrate the superiority and generalizability of Uni-Inv and Uni-Edit, even under low-cost settings. Project page: https://uniedit-flow.github.io/
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。
