发表机构
Tsinghua University; Renmin University of China（清华大学; 中国人民大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SR-Edit是一种图像编辑框架，通过迭代自细化解决现有方法区域估计不准、易产生伪影的问题，实验表明其在区域保留和图像质量上优于现有技术。
AI 中文摘要
随着生成模型的快速发展，图像编辑已取得显著进展，但要实现仅精确修改目标区域、同时严格保留所有其他区域的忠实编辑仍具挑战性。由于实践中往往难以获取外部提供的区域标注，越来越多的研究致力于通过自动推断编辑区域与非编辑区域，并对非编辑区域实施一致性约束来提升保留效果。然而，这些方法仍存在区域估计不准确、启发式校正策略扭曲原生推理过程的问题，使得旨在提升忠实度的方法本身成为新的伪影来源。我们提出SR-Edit，这是一种通过迭代自细化克服上述问题的图像编辑框架。具体而言，在每次迭代中，SR-Edit首先（i）通过轻量后处理从模型自身预测中提取逐步精确且自一致的区域划分，随后（ii）通过与原始采样动态保持一致的校正更新来实现非编辑区域的保留。大量实验表明，与现有编辑技术相比，SR-Edit实现了更优的区域保留效果和整体图像质量。
英文摘要
With the recent rapid progress in generative models, image editing has made remarkable advances, yet achieving faithful edits that precisely modify only the target regions while strictly preserving all other regions remains challenging. Since externally provided region annotations are often difficult to obtain in practice, a growing body of work seeks to improve preservation by automatically inferring edit and non-edit regions, and then enforcing consistency on the latter. However, these approaches still suffer from inaccurate region estimation and heuristic correction strategies that distort the native inference process, making methods designed for fidelity themselves a new source of artifacts. We propose SR-Edit, an image editing framework that overcomes these issues via iterative self-refinement. Specifically, at each iteration, SR-Edit first (i) extracts progressively precise and self-consistent region separation from the model's own predictions by lightweight post-processing, and then (ii) enforces preservation in non-edit areas through correction updates that remain aligned with the original sampling dynamics. Extensive experiments demonstrate that SR-Edit achieves superior preservation and overall image quality compared to existing editing techniques.
