小波引导的语义信号补偿用于无反转图像编辑
Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing
AI总结：
针对无反转图像编辑中全局属性编辑不足的问题，提出基于小波的频率感知语义补偿策略，在生成早期增强有效信号，提升全局编辑能力同时保持背景保真度。
摘要：
文本引导的图像编辑旨在根据目标提示修改视觉内容，同时保留背景。最近的无反转图像编辑框架（如FlowEdit）展示了无需反转的强大编辑能力。实验表明，在适当的超参数设置下，FlowEdit可以实现显著的语义变化。然而，我们观察到在某些全局属性偏移下，编辑轨迹在早期时间步可能无法有效远离源分布。我们的分析表明，在高噪声区域，主导的流趋向数据流形，这降低了文本条件方向的影响，导致全局修改有限，而背景结构仅得到中等程度的保留。受此观察启发，我们提出了一种无反转、频率感知的语义补偿策略，在生成早期阶段增强有效信号，同时保持背景的结构一致性。所提方法在不牺牲背景保真度的情况下提高了全局编辑能力。
英文摘要：
Text-guided image editing aims to modify visual content according to a target prompt while preserving the background. Recent inversion-free image editing frameworks such as FlowEdit have demonstrated strong editing capability without requiring inversion. Empirically, FlowEdit can achieve substantial semantic changes under appropriate hyperparameter settings. However, we observe that under certain global attribute shifts, the editing trajectory may not effectively move away from the source distribution in the early timesteps. Our analysis suggests that in the high-noise regime, the dominant manifold-seeking flow toward the data manifold can reduce the influence of the text-conditioned direction, leading to limited global modification while background structures remain only moderately preserved. Inspired by this observation, we propose an inversion-free, frequency-aware semantic compensation strategy that strengthens the effective signal in the early stage of generation, while maintaining structural consistency in the background. The proposed method improves global editing capacity without sacrificing background fidelity.
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。
