A Comparative Study of Image Restoration Networks for General Backbone Network Design

TL;DR

This paper compares various image restoration networks across multiple tasks, analyzes their strengths and weaknesses, and proposes a new general backbone network, X-Restormer, that achieves state-of-the-art results and broad task applicability.

Contribution

It introduces a comprehensive comparative analysis of existing networks and proposes a novel general backbone network, X-Restormer, for diverse image restoration tasks.

Findings

X-Restormer achieves state-of-the-art performance across multiple tasks.

Different networks exhibit varying strengths depending on the task.

The proposed backbone network demonstrates strong task generality.

Abstract

Despite the significant progress made by deep models in various image restoration tasks, existing image restoration networks still face challenges in terms of task generality. An intuitive manifestation is that networks which excel in certain tasks often fail to deliver satisfactory results in others. To illustrate this point, we select five representative networks and conduct a comparative study on five classic image restoration tasks. First, we provide a detailed explanation of the characteristics of different image restoration tasks and backbone networks. Following this, we present the benchmark results and analyze the reasons behind the performance disparity of different models across various tasks. Drawing from this comparative study, we propose that a general image restoration backbone network needs to meet the functional requirements of diverse tasks. Based on this principle, we design a new general image restoration backbone network, X-Restormer. Extensive experiments demonstrate that X-Restormer possesses good task generality and achieves state-of-the-art performance across a variety of tasks.