跟随你的形状：通过轨迹引导的区域控制实现形状感知图像编辑
Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control
AI总结：
Follow-Your-Shape通过轨迹引导的区域控制实现精准形状编辑，无需训练和掩码，提升大规模形状变换任务的编辑性和视觉保真度。
摘要：
尽管最近的基于流的图像编辑模型在多样任务中展现出通用能力，但它们往往在挑战性场景中难以专业化，尤其是涉及大规模形状变换的场景。在执行此类结构性编辑时，这些方法要么无法实现预期的形状变化，要么无意中改变非目标区域，导致背景质量下降。我们提出了Follow-Your-Shape，一种无需训练和无需掩码的框架，支持在严格保留非目标内容的情况下对物体形状进行精确可控的编辑。受反向和编辑轨迹之间的分歧启发，我们通过比较反向和去噪路径中逐个token的速度差异计算轨迹分歧图（TDM）。TDM能够精确定位可编辑区域，并引导一种调度的KV注入机制，确保编辑的稳定和忠实。为了促进严格评估，我们引入了ReShapeBench，一个新的包含120张新图像和丰富提示对的基准，专门针对形状感知编辑进行了定制。实验表明，我们的方法在需要大规模形状替换的任务中实现了优越的编辑性和视觉保真度。
英文摘要：
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.
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。
