发表机构
East China Normal University; The Hong Kong University of Science and Technology（华东师范大学; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出h-Flow，一个无需训练且基于理论的基于流的图像编辑框架。受杜布h变换启发，将图像编辑重述为条件生成，通过构建等效SDE扩展h变换，设计专用h函数并引入速度正交分解，实现有效、稳健且灵活的图像编辑。
AI 中文摘要
使用预训练的文本到图像流模型编辑图像通常需要仔细平衡目标对齐与期望提示以及源与原始图像的一致性。现有方法要么依赖基于反演的管道，要么依赖启发式的源到目标轨迹构建，这通常依赖于特定于架构的设计或对超参数敏感。本文提出了h-Flow，一个无需训练且基于理论的基于流的编辑框架。受杜布h变换启发，将图像编辑重新表述为在对应源一致性和目标对齐的多个终端事件下的条件生成。首先通过构建具有相同边际的等效SDE将经典h变换从基于SDE的模型扩展到确定性RF框架。在此框架内，为源一致性和目标对齐设计了专用的h函数，产生封闭形式的重建指导和基于速度的语义编辑信号。还引入了速度正交分解来解耦重建和编辑方向，实现两个目标之间的可控权衡。大量实验表明h-Flow在各种场景中都能实现有效、稳健和灵活的编辑。代码即将发布。
英文摘要
Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original image. Existing approaches either rely on inversion-based pipelines or heuristic source-to-target trajectory constructions, which often depend on architecture-specific designs or are sensitive to hyperparameters. In this paper, we propose h-Flow, a training-free and theoretically grounded flow-based editing framework. Inspired by Doob's $h$-Transform, we reformulate image editing as conditional generation under multiple terminal events corresponding to source consistency and target alignment. We first extend the classical $h$-Transform from SDE-based models to the deterministic RF framework by constructing an equivalent SDE with identical marginals. Within this formulation, we design dedicated $h$-functions for source consistency and target alignment, yielding closed-form reconstruction guidance and velocity-based semantic editing signals. We further introduce a velocity orthogonal decomposition to decouple reconstruction and editing directions, enabling a controllable trade-off between the two objectives. Extensive experiments demonstrate that h-Flow achieves effective, robust, and flexible editing across diverse scenarios. The code will be released soon.
