arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.08059cs.CVcs.AI

ImageEdit-R1: 通过强化学习提升多智能体图像编辑

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning

National University of Singapore（新加坡国立大学）；Adobe Research（Adobe研究）

Yiran Zhao, Yaoqi Ye, Xiang Liu, Michael Qizhe Shieh, Trung Bui

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

ImageEdit-R1通过强化学习实现多智能体图像编辑，提升复杂指令下的编辑效果与上下文感知能力。

摘要：

随着商业多模态模型的快速发展，图像编辑因其在日常生活中的广泛应用而受到广泛关注。尽管取得了显著进展，现有的图像编辑系统，特别是闭源或专有模型，往往在处理复杂、间接或多步骤的用户指令时存在困难。这些局限性阻碍了它们执行细致、基于上下文的编辑能力，以符合人类意图。在本工作中，我们提出了ImageEdit-R1，一种用于智能图像编辑的多智能体框架，利用强化学习协调一组预训练的视觉-语言和生成智能体的高层决策。每个智能体负责不同的能力——如理解用户意图、识别感兴趣区域、选择适当的编辑操作以及合成视觉内容——而强化学习则管理它们的协作，以确保一致且目标导向的行为。与现有方法依赖单体模型或手工制定流程不同，我们的方法将图像编辑视为一个序列决策问题，使动态和基于上下文的编辑策略成为可能。实验结果表明，ImageEdit-R1在多个图像编辑数据集上始终优于单独的闭源扩散模型和替代多智能体框架基线。

英文摘要：

With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly closed-source or proprietary models, often struggle with complex, indirect, or multi-step user instructions. These limitations hinder their ability to perform nuanced, context-aware edits that align with human intent. In this work, we propose ImageEdit-R1, a multi-agent framework for intelligent image editing that leverages reinforcement learning to coordinate high-level decision-making across a set of specialized, pretrained vision-language and generative agents. Each agent is responsible for distinct capabilities--such as understanding user intent, identifying regions of interest, selecting appropriate editing actions, and synthesizing visual content--while reinforcement learning governs their collaboration to ensure coherent and goal-directed behavior. Unlike existing approaches that rely on monolithic models or hand-crafted pipelines, our method treats image editing as a sequential decision-making problem, enabling dynamic and context-aware editing strategies. Experimental results demonstrate that ImageEdit-R1 consistently outperforms both individual closed-source diffusion models and alternative multi-agent framework baselines across multiple image editing datasets.

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。

↑