用智能代理系统自动解决复杂图像修复问题
An Intelligent Agentic System for Complex Image Restoration Problems
- 模仿人类解题流程，分五步动态调度修复模型
- 通过自探索学习积累经验，提升修复决策能力
- 适合需要多模型协同的复杂图像修复场景
真实世界图像修复（IR）本质上复杂，常需组合多个专用模型应对多样退化。受人类问题解决启发，我们提出AgenticIR，一种模拟人类处理图像流程的智能代理系统，遵循感知、调度、执行、反思和重调度五个关键阶段。该系统利用大语言模型（LLMs）和视觉语言模型（VLMs）通过文本生成交互，动态操作一个图像修复模型工具箱。我们对VLMs进行微调以实现图像质量分析，并使用LLMs进行推理，逐步引导系统运行。为弥补LLMs在特定IR知识与经验上的不足，引入自探索方法，使LLM能观察并总结修复结果，形成可参考的文档。实验表明，AgenticIR在处理复杂IR任务上具有潜力，为实现视觉处理中的通用智能提供了有前景的路径。
原文摘要 · Abstract (English)
Real-world image restoration (IR) is inherently complex and often requires combining multiple specialized models to address diverse degradations. Inspired by human problem-solving, we propose AgenticIR, an agentic system that mimics the human approach to image processing by following five key stages: Perception, Scheduling, Execution, Reflection, and Rescheduling. AgenticIR leverages large language models (LLMs) and vision-language models (VLMs) that interact via text generation to dynamically operate a toolbox of IR models. We fine-tune VLMs for image quality analysis and employ LLMs for reasoning, guiding the system step by step. To compensate for LLMs' lack of specific IR knowledge and experience, we introduce a self-exploration method, allowing the LLM to observe and summarize restoration results into referenceable documents. Experiments demonstrate AgenticIR's potential in handling complex IR tasks, representing a promising path toward achieving general intelligence in visual processing.
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。