RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
This addresses the challenge of time-consuming and suboptimal manual or all-in-one methods for image restoration, offering a flexible and scalable solution for mobile device users and applications.
The paper tackles the problem of restoring images with multiple degradations like noise, blur, and low light by introducing RestoreAgent, an autonomous system that uses multimodal large language models to assess degradation and optimize restoration tasks, models, and sequences, achieving superior performance over human experts.
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 modular design facilitates the fast integration of new tasks and models, enhancing its flexibility and scalability for various applications.