通过轨迹直线度选择最优反向路径，提升图像逆向生成精度。
Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness
- 基于轨迹直线度筛选固定点解，优化反向生成路径
- 在FLUX.1-dev和PIE-Bench上实现更优的图像重建与编辑效果
- 无需训练即可提升生成质量，适合图像编辑应用
找到生成给定数据样本的初始噪声（即逆向生成）是无训练图像编辑等下游任务的关键。现有固定点逆向方法将每一步逆向建模为固定点问题，但缺乏从多个可能解中选择的合理机制。我们发现不同选择会导致显著不同的逆向轨迹，进而影响重建与编辑质量。针对修正流模型，我们进一步发现这种差异与轨迹直线度密切相关，因此提出以直线度作为选择准则。我们提出SelFix方法，在保持标准局部假设下收敛到精确逆根的同时，优先选择产生更直逆向轨迹的解。在FLUX.1-dev和PIE-Bench上的实验表明，SelFix优于现有逆向基线，实现了更强的真实图像重建与更好的源图像保留提示编辑效果。代码已开源。
原文摘要 · Abstract (English)
Finding the initial noise that generates a given data sample, known as inversion, is a key component for downstream applications such as training-free image editing. Existing fixed-point inversion methods improve inversion accuracy by formulating each inversion step as a fixed-point problem, but they lack a principled mechanism for selecting among multiple fixed-point solutions that can arise in practice. We observe that different selections induce different inversion trajectories, leading to substantial variation in reconstruction and editing quality. For rectified flows, we further find that this variation is closely associated with trajectory straightness, motivating straightness as a principled selection criterion. We propose SelFix, a fixed-point inversion method that selects fixed-point solutions inducing straighter inverse trajectories while retaining convergence to an exact inverse root under standard local assumptions. Experiments on FLUX.1-dev and PIE-Bench show that SelFix improves fixed-point inversion, achieving stronger real-image reconstruction and better source-preserving prompt-based editing than prior inversion baselines. The code is available at https://github.com/seminkim/selfix.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。