FreqEdit：保留高频特征以实现鲁棒的多轮图像编辑
FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
针对多轮指令编辑中高频细节逐步丢失的问题，提出从参考速度场注入高频特征、空间自适应调制注入强度、并周期性重校准编辑轨迹的免训练方案，可直接用于提升现有扩散编辑模型在长链迭代下的身份保持与指令跟随能力。
原文依据 we identify progressive loss of high-frequency information as the primary cause of this quality degradation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于指令的自然语言图像编辑已成为一种强大的直观视觉操作范式。尽管近期模型在单次编辑上取得了令人印象深刻的结果，但在多轮编辑下会出现严重的质量退化。通过系统分析，我们确认高频信息的逐步丢失是这一质量退化的主要原因。我们提出 FreqEdit，一个免训练框架，可在 10 次以上连续迭代中实现稳定编辑。我们的方法由三个协同组件构成：（1）从参考速度场注入高频特征以保留细粒度细节；（2）一种自适应注入策略，在空间上调制注入强度以实现精确的区域特定控制；（3）一种路径补偿机制，周期性重校准编辑轨迹以防止过度约束。大量实验表明，与七个最优基线相比，FreqEdit 在身份保持和指令跟随两方面均取得更优性能。
英文原文摘要 1079 字符
Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under multi-turn editing. Through systematic analysis, we identify progressive loss of high-frequency information as the primary cause of this quality degradation. We present FreqEdit, a training-free framework that enables stable editing across 10+ consecutive iterations. Our approach comprises three synergistic components: (1) high-frequency feature injection from reference velocity fields to preserve fine-grained details, (2) an adaptive injection strategy that spatially modulates injection strength for precise region-specific control, and (3) a path compensation mechanism that periodically recalibrates the editing trajectory to prevent over-constraint. Extensive experiments demonstrate that FreqEdit achieves superior performance in both identity preservation and instruction following compared to seven state-of-the-art baselines.