Edit-GRPO: 一种用于图像编辑的保持局部性的策略优化框架
Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
AI总结：
本文提出Edit-GRPO框架，通过分离编辑与保留目标，解决图像编辑中保持局部性与全局一致性的问题，提升编辑效果并减少上下文扭曲等常见伪影。
摘要：
图像编辑中的一个根本性挑战在于保持空间局部性：编辑应改进目标内容而不应无意地改变周围区域。然而，大多数基于优化的编辑方法将图像视为整体实体，导致全局策略更新，从而破坏局部性并引入不期望的上下文变化。我们观察到，这一问题源于局部编辑意图与全局应用的优化信号之间的不匹配。受此启发，我们提出Edit-GRPO，一种在优化图像编辑时保持局部性的策略优化框架，该框架明确地将编辑和保留目标分离。通过为编辑和非编辑区域分配区域特定的优化信号，Edit-GRPO使策略更新与编辑任务的空间结构对齐，从而实现局部改进同时保持全局视觉一致性。这种设计有效抑制了诸如上下文扭曲和边界不一致等常见伪影。在各种图像编辑场景中的广泛实验表明，与现有基于优化的方法相比，Edit-GRPO在显著提高局部性保持的同时，保持了强大的编辑性能，验证了所提框架的通用性和有效性。
英文摘要：
A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, most optimization-based editing approaches treat images as holistic entities, causing global policy updates that undermine locality and introduce undesired context changes. We observe that this issue stems from a mismatch between localized editing intent and globally applied optimization signals. Motivated by this insight, we propose Edit-GRPO, preserving Locality while optimizing image editing, a locality-preserving policy optimization framework that explicitly decouples editing and preservation objectives. By assigning region-specific optimization signals to edit and non-edit areas, Edit-GRPO aligns policy updates with the spatial structure of editing tasks, enabling localized improvements while maintaining global visual coherence. This design effectively suppresses common artifacts such as context distortion and boundary inconsistency. Extensive experiments across diverse image editing scenarios demonstrate that Edit-GRPO significantly improves locality preservation while maintaining strong editing performance compared to existing optimization-based methods, validating the generality and effectiveness of the proposed framework.
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。
