SteerFlow：通过修正流实现忠实的基于反向的图像编辑
SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing
AI总结：
SteerFlow通过引入隐式直线化求解器和轨迹插值，提升图像编辑的源保真度，实验表明其在FLUX.1-dev和Stable Diffusion 3.5 Medium上表现更优。
摘要：
近期基于流的生成模型的进步使得通过将图像转换为潜在噪声并重新生成来实现免训练、文本引导的图像编辑成为可能。然而，现有方法在保持源保真度方面存在困难：高阶求解器会增加模型推断，截断反向会限制可编辑性，而特征注入方法缺乏架构可转移性。为了解决这些限制，我们提出了SteerFlow，一个模型无关的编辑框架，具有强的理论保证。在正向过程中，我们引入了Amortized Fixed-Point Solver，通过在连续时间步之间强制速度一致性，隐式地使正向轨迹直线化，从而产生高保真的反向潜在。在反向过程中，我们引入了轨迹插值，通过自适应混合目标编辑和源重建速度，使编辑轨迹保持在源上。为了进一步提高背景保真度，我们引入了自适应掩码机制，通过概念引导的分割和源-目标速度差异空间约束编辑信号。在FLUX.1-dev和Stable Diffusion 3.5 Medium上的大量实验表明，SteerFlow在编辑质量上优于现有方法。最后，我们展示了SteerFlow可以自然扩展到复杂的多轮编辑范式，而不会积累漂移。
英文摘要：
Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods struggle to preserve source fidelity: higher-order solvers incur additional model inferences, truncated inversion constrains editability, and feature injection methods lack architectural transferability. To address these limitations, we propose SteerFlow, a model-agnostic editing framework with strong theoretical guarantees on source fidelity. In the forward process, we introduce an Amortized Fixed-Point Solver that implicitly straightens the forward trajectory by enforcing velocity consistency across consecutive timesteps, yielding a high-fidelity inverted latent. In the backward process, we introduce Trajectory Interpolation, which adaptively blends target-editing and source-reconstruction velocities to keep the editing trajectory anchored to the source. To further improve background preservation, we introduce an Adaptive Masking mechanism that spatially constrains the editing signal with concept-guided segmentation and source-target velocity differences. Extensive experiments on FLUX.1-dev and Stable Diffusion 3.5 Medium demonstrate that SteerFlow consistently achieves better editing quality than existing methods. Finally, we show that SteerFlow extends naturally to a complex multi-turn editing paradigm without accumulating drift.
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。
