从计划到像素：学习计划与协调以实现开放性图像编辑
From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
AI总结：
本文提出一种长期视图图像编辑框架，通过规划器生成结构化原子分解和协调器选择工具和区域执行每一步，结合视觉语言判断者提供基于结果的奖励，提升编辑的连贯性和可靠性。
摘要：
现代图像编辑模型能产生逼真结果，但难以处理抽象的多步骤指令（如'使此广告更素食化'）。先前基于代理的方法将此类任务分解，但依赖手工管道或教师模仿，限制了灵活性并使学习脱离实际编辑结果。我们提出一种长期视图图像编辑框架，其中规划器生成结构化原子分解，协调器选择工具和区域执行每一步。视觉语言判断者提供基于结果的奖励以确保指令遵循和视觉质量。协调器被训练以最大化这些奖励，成功轨迹用于优化规划器。通过紧密耦合规划与奖励驱动执行，我们的方法比单步或基于规则的多步基线产生了更连贯和可靠的编辑。
英文摘要：
Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.
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。
