用简单方法让流模型修复图像更准，不改模型也不重训练。
FlowSteer: Conditioning Flow Field for Consistent Image Restoration
- 在采样路径上注入测量先验，结合模型隐式引导与显式约束。
- 零样本下提升超分辨率、去模糊等任务的还原准确率和身份保真度。
- 无需微调或适配器，适合快速部署到多种图像修复场景。
基于流的文本到图像生成模型在提示驱动生成中表现优异，但在图像修复任务中常因偏离测量数据而失真。现有方法依赖数据特定流或任务专用适配器，计算开销大且难以跨任务扩展。本文提出FlowSteer（FS），一种操作感知的条件化方案，通过在采样路径上注入测量先验，将冻结流模型的隐式引导与显式测量约束相结合。在超分辨率、去模糊、去噪和着色任务中，FS 在严格零样本设置下显著提升测量一致性与身份保真度，无需重新训练模型或引入适配器。我们揭示了流模型对噪声的敏感性如何指导调度设计。尽管结构简单，FS 仍能实现更高重建保真度，同时充分利用流模型丰富的生成先验。所有数据与代码将公开于该链接。
原文摘要 · Abstract (English)
Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. Prior work mitigate this drift with data-specific flows or task-specific adapters that are computationally heavy and not scalable across tasks. This raises the question "Can't we efficiently manipulate the existing generative capabilities of a flow model?" To this end, we introduce FlowSteer (FS), an operator-aware conditioning scheme that injects measurement priors along the sampling path,coupling a frozed flow's implicit guidance with explicit measurement constraints. Across super-resolution, deblurring, denoising, and colorization, FS improves measurement consistency and identity preservation in a strictly zero-shot setting-no retrained models, no adapters. We show how the nature of flow models and their sensitivities to noise inform the design of such a scheduler. FlowSteer, although simple, achieves a higher fidelity of reconstructed images, while leveraging the rich generative priors of flow models. All data and code will be publicly available \href{https://tharindu-nirmal.github.io/FlowSteer/}{in this link}.
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。