形隨意動：基於軌跡引導區域控制的形狀感知圖像編輯

摘要

尽管近期的基于流的图像编辑模型展现了跨多种任务的通用能力，但在处理具有挑战性的场景时，尤其是涉及大规模形状变换的情况，这些模型往往难以专精。在执行此类结构性编辑时，这些方法要么未能实现预期的形状改变，要么无意中改变了非目标区域，导致背景质量下降。我们提出了“随形而动”（Follow-Your-Shape），一个无需训练且无需掩码的框架，支持精确且可控的对象形状编辑，同时严格保护非目标内容。受反转与编辑轨迹间差异的启发，我们通过比较反转路径与去噪路径间逐令牌的速度差异，计算出一个轨迹差异图（Trajectory Divergence Map, TDM）。TDM能够精确定位可编辑区域，并指导一个预定的键值注入机制（Scheduled KV Injection），确保编辑过程的稳定性和忠实性。为了促进严谨的评估，我们引入了ReShapeBench，这是一个包含120张新图像及丰富提示对的新基准，专门为形状感知编辑而设计。实验表明，我们的方法在可编辑性和视觉保真度上均表现出色，特别是在需要大规模形状替换的任务中。

English

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.

形隨意動：基於軌跡引導區域控制的形狀感知圖像編輯

Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

摘要

Support