FlowDC：面向复杂图像编辑的基于流的解耦-衰减方法
FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing
把复杂多目标编辑拆成多个子编辑效果并在流匹配速度场上并行叠加，同时对与编辑位移正交的速度分量做衰减以保住源图结构——这套「速度分解+正交分量衰减」可直接迁移到任何基于 flow matching 的编辑/可控生成管线中，用于缓解多条件叠加时的结构漂移。
原文依据 we decompose the velocity and decay the orthogonal part for better source consistency
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着预训练文本到图像流匹配模型的激增，基于文本的图像编辑性能获得了显著提升，尤其是仅包含单一编辑目标的简单编辑。然而，为满足爆炸式增长的编辑需求，包含多个编辑目标的复杂编辑成为更具挑战性的任务。现有复杂编辑方案——单轮编辑与多轮编辑——分别受限于长文本跟随能力和累积不一致性。因此，它们难以在语义对齐与源一致性之间取得平衡。本文提出 FlowDC，将复杂编辑解耦为多个子编辑效果，并在编辑过程中并行叠加。同时，我们观察到与编辑位移正交的速度量会损害源结构的保持。因此，我们对速度进行分解，并对正交部分进行衰减，以获得更好的源一致性。为评估复杂编辑设置的有效性，我们构建了一个复杂编辑基准：Complex-PIE-Bench。在两个基准上，FlowDC 相比现有方法展现出更优的结果。我们还详细给出了模块设计的消融实验。
英文原文摘要 1270 字符
With the surge of pre-trained text-to-image flow matching models, text-based image editing performance has gained remarkable improvement, especially for **simple editing** that only contains a single editing target. However, to satisfy the exploding editing requirements, the **complex editing** that contains multiple editing targets is posed as a more challenging task. However, current complex editing solutions: single-round and multi-round editing are limited by long text following and cumulative inconsistency, respectively. Thus, they struggle to strike a balance between semantic alignment and source consistency.In this paper, we propose **FlowDC**, which decouples the complex editing into multiple sub-editing effects and superposes them in parallel during the editing process. Meanwhile, we observed that the velocity quantity that is orthogonal to the editing displacement harms the source structure preserving. Thus, we decompose the velocity and decay the orthogonal part for better source consistency.To evaluate the effectiveness of complex editing settings, we construct a complex editing benchmark: Complex-PIE-Bench. On two benchmarks, FlowDC shows superior results compared with existing methods. We also detail the ablations of our module designs.