约束编辑场用于免训练流编辑
Constrained Edit Fields for Training-Free Flow Editing
- Imperial College London（帝国理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出约束编辑场（CEF），通过为空间位置分配编辑责任并分解编辑场，实现免训练流编辑，在PIE-Bench上达到最先进的背景保持效果。
AI中文摘要：
文本引导的图像编辑旨在执行所需的编辑，同时保留与编辑无关的源内容。预训练的整流流模型通过修改采样轨迹，实现对真实图像的免训练编辑。然而，与所需编辑无关的位置的响应仍可能沿编辑轨迹累积，并在最终结果中显现。为克服这一问题，我们提出约束编辑场（CEF），为每个空间位置分配一个连续的编辑责任度，量化其与所需编辑的相关性。当相关内容存在于源图像中时，CEF直接从源图像估计编辑责任。对于目标内容在源中缺失的编辑，CEF首先生成一个无约束提议以揭示其实际空间支持，然后从该提议估计责任。在每个编辑步骤中，CEF将基础编辑场分解为提示诱导和轨迹诱导两个分量，使编辑责任能够保留与指令相关的更新，同时抑制非预期的轨迹诱导变化。在全部700个PIE-Bench示例上的评估中，CEF在Stable Diffusion 3.5 Medium和FLUX上均实现了最先进的结构距离、背景LPIPS和背景MSE，同时保持有竞争力的指令对齐。在Stable Diffusion 3.5 Medium上，这些指标分别较先前最佳结果降低了10.2%、21.2%和48.0%。
英文摘要：
Text-guided image editing aims to perform a desired edit while preserving source content unrelated to it. Pretrained rectified-flow models enable training-free editing of real images through modifications to their sampling trajectories. However, responses at locations unrelated to the desired edit can still accumulate along the editing trajectory and become visible in the final result. To overcome this, we propose Constrained Edit Fields (CEF), which assigns each spatial location a continuous edit responsibility that quantifies its relevance to the desired edit. CEF estimates edit responsibility directly from the source image when the relevant content is present. For edits whose target content is absent from the source, CEF first generates an unconstrained proposal to reveal its realized spatial support and then estimates responsibility from that proposal. At each editing step, CEF decomposes the base edit field into prompt-induced and trajectory-induced components, enabling edit responsibility to preserve instruction-relevant updates while suppressing unintended trajectory-induced changes. Evaluated on all 700 PIE-Bench examples, CEF achieves state-of-the-art Structure Distance, background LPIPS, and background MSE with both Stable Diffusion 3.5 Medium and FLUX, while retaining competitive instruction alignment. On Stable Diffusion 3.5 Medium, it reduces these metrics over the previous best results by 10.2%, 21.2%, and 48.0%, respectively.
