VeloEdit: 无需训练的一致且连续的基于指令的图像编辑 via 速度场分解
VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition
AI总结：
VeloEdit通过速度场分解实现无需训练的一致且连续的基于指令的图像编辑，通过动态识别编辑区域并采用速度插值控制编辑强度，提升视觉一致性和编辑连续性。
摘要：
基于指令的图像编辑旨在根据文本指令修改源内容。然而，现有方法基于流匹配往往因去噪诱导的重建误差导致非编辑区域的一致性下降，并且缺乏对编辑强度的精细控制。为此，我们提出VeloEdit，一种无需训练的方法，能够实现高度一致且连续可控的编辑。VeloEdit通过量化负责保留源内容的速度场与驱动所需编辑的速度场之间的差异来动态识别编辑区域。基于此划分，我们通过将编辑速度替换为源恢复速度来强制一致性，同时通过速度插值在目标区域连续调节编辑强度。与以往依赖复杂注意力操作或辅助可训练模块的方法不同，VeloEdit直接在速度场上操作。在Flux.1 Kontext和Qwen-Image-Edit上的大量实验表明，VeloEdit在几乎不增加额外计算成本的情况下提升了视觉一致性和编辑连续性。代码可在https://github.com/xmulzq/VeloEdit获取。
英文摘要：
Instruction-based image editing aims to modify source content according to textual instructions. However, existing methods built upon flow matching often struggle to maintain consistency in non-edited regions due to denoising-induced reconstruction errors that cause drift in preserved content. Moreover, they typically lack fine-grained control over edit strength. To address these limitations, we propose VeloEdit, a training-free method that enables highly consistent and continuously controllable editing. VeloEdit dynamically identifies editing regions by quantifying the discrepancy between the velocity fields responsible for preserving source content and those driving the desired edits. Based on this partition, we enforce consistency in preservation regions by substituting the editing velocity with the source-restoring velocity, while enabling continuous modulation of edit intensity in target regions via velocity interpolation. Unlike prior works that rely on complex attention manipulation or auxiliary trainable modules, VeloEdit operates directly on the velocity fields. Extensive experiments on Flux.1 Kontext and Qwen-Image-Edit demonstrate that VeloEdit improves visual consistency and editing continuity with negligible additional computational cost. Code is available at https://github.com/xmulzq/VeloEdit.
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。
