Divide and Restore: A Modular Task-Decoupled Framework for Universal Image Restoration

TL;DR

This paper introduces a modular, task-decoupled image restoration framework that uses a diagnostic router to dynamically select specialized restoration modules, reducing training complexity and improving scalability for various degradation types.

Contribution

The proposed framework enables flexible, task-specific image restoration with minimal retraining, contrasting with monolithic models that require extensive joint training.

Findings

Achieves scalable multi-degradation restoration on standard hardware.

Reduces training overhead by isolating reconstruction paths.

Allows easy addition of new degradation types with minimal retraining.

Abstract

Restoring images affected by various types of degradation, such as noise, blur, or improper exposure, remains a significant challenge in computer vision. While recent trends favor complex monolithic all-in-one architectures, these models often suffer from negative task interference and require extensive joint training cycles on high-end computing clusters. In this paper, we propose a modular, task-decoupled image restoration framework based on an explicit diagnostic routing mechanism. The architecture consists of a lightweight Convolutional Neural Network (CNN) classifier that evaluates the input image and dynamically directs it to a specialized restoration node. A key advantage of this framework is its model-agnostic extensibility: while we demonstrate it using three independent U-Net experts, the system allows for the integration of any restoration method tailored to specific tasks. By isolating reconstruction paths, the framework prevents feature conflicts and significantly reduces training overhead. Unlike monolithic models, adding new degradation types in our framework only requires training a single expert and updating the router, rather than a full system retraining. Experimental results demonstrate that this computationally accessible approach offers a scalable and efficient solution for multi-degradation restoration on standard local hardware. The code will be published upon paper acceptance.