RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models

TL;DR

RestoreAgent is an autonomous, multimodal large language model-based system that intelligently assesses and restores images with multiple degradations, outperforming traditional methods and supporting flexible, scalable integration of new tasks.

Contribution

The paper introduces RestoreAgent, a novel autonomous image restoration system that dynamically determines and executes optimal restoration strategies using multimodal large language models.

Findings

RestoreAgent outperforms human experts in complex image restoration tasks.

The system effectively handles multiple degradations in a unified framework.

Modular design allows easy integration of new restoration tasks and models.

Abstract

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.