让普通用户也能轻松精准编辑图片，还能看清每一步操作理由。
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment
- 分三阶段训练，用16个可解释工具逐步操作图片
- 像素误差更低，摘要准确率更高，比基线提升明显
- 适合需要透明可追溯编辑过程的普通用户或设计师
当前图像编辑软件依赖固定滤镜或专家调参，难以匹配普通用户的意图。生成式模型常出现伪影、不合理细节或风格失真，且无法解释修改原因。我们提出IEA，一种对话式图像编辑代理，通过显式可解释的动作空间操作16个参数化工具。训练采用三阶段多任务流程：(1) 在压缩版专家编辑数据上进行监督微调；(2) 通过GRPO优化，奖励图像相似度提升、工具有效性及意图总结；(3) 大规模合成数据微调，联合掌握编辑、优化与意图总结能力。通过逐步操控工具，IEA生成可检查和调试的编辑轨迹。定量实验显示，其在编辑任务上像素距离更低，在摘要任务上ROUGE-L更高；用户研究中，其指令遵循能力优于工具调用方法，整体感知质量超越生成式方法。结果验证了以工具为中心的可解释视觉语言模型是人机指令引导图像润色的可靠路径。
原文摘要 · Abstract (English)
Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes. Creations by generative models may contain artifacts, implausible details, or stylistic drift away from photorealism and offer little insight into why an edit was made. We propose IEA, a conversational Image Editing Agent that learns to operate parameterized tools in an explicit, interpretable action space. IEA is trained via a three-stage multitask pipeline: (1) SFT on distilled expert edits, (2) GRPO with rewards for likeness improvement, tool usefulness, and intent summarization, and (3) large-scale synthetic fine-tuning to jointly master image editing, refinement, and user intent summarization. By manipulating 16 editing tools step by step, IEA produces transparent edit traces that can be inspected and debugged. In quantitative experiments, it attains a lower pixel distance on the edit task and a higher ROUGE-L on the summary task than strong baselines. In user studies, it ranks best among tool-calling methods for instruction following while surpassing generative methods in overall perceptual quality. Our results validate interpretable, tool-centric VLMs as a reliable path to human instruction-guided image retouching.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。