RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models

Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system’s modular design facilitates the fast integration of new tasks and models.

Authors

• Haoyu Chen University of Oulu
• Wenbo Li The Chinese University of Hong Kong
• Jinjin Gu The University of Sydney
• Jingjing Ren The Hong Kong University of Science and Technology (Guangzhou)
• Sixiang Chen The Hong Kong University of Science and Technology (Guangzhou), China
• Tian Ye The Hong Kong University of Science and Technology (Guangzhou), China
• Renjing Pei Huawei Noah’s Ark Lab
• Kaiwen Zhou The Chinese University of Hong Kong
• Fenglong Song Huawei Noah's Ark Lab
• Lei Zhu

Keywords

No keywords are indexed for this paper.