A Preliminary Exploration Towards General Image Restoration

TL;DR

This paper introduces the concept of general image restoration (GIR), aiming to unify various image restoration tasks within a single model to improve generalization and handle complex real-world degradations.

Contribution

It defines GIR, establishes new datasets and evaluation frameworks, and analyzes existing approaches to address the challenges of generalization and complex degradations in image restoration.

Findings

Existing models struggle with generalization in real-world scenarios.

GIR can unify multiple restoration tasks for broader applicability.

Evaluation reveals strengths and challenges of current approaches.

Abstract

Despite the tremendous success of deep models in various individual image restoration tasks, there are at least two major technical challenges preventing these works from being applied to real-world usages: (1) the lack of generalization ability and (2) the complex and unknown degradations in real-world scenarios. Existing deep models, tailored for specific individual image restoration tasks, often fall short in effectively addressing these challenges. In this paper, we present a new problem called general image restoration (GIR) which aims to address these challenges within a unified model. GIR covers most individual image restoration tasks (\eg, image denoising, deblurring, deraining and super-resolution) and their combinations for general purposes. This paper proceeds to delineate the essential aspects of GIR, including problem definition and the overarching significance of generalization performance. Moreover, the establishment of new datasets and a thorough evaluation framework for GIR models is discussed. We conduct a comprehensive evaluation of existing approaches for tackling the GIR challenge, illuminating their strengths and pragmatic challenges. By analyzing these approaches, we not only underscore the effectiveness of GIR but also highlight the difficulties in its practical implementation. At last, we also try to understand and interpret these models' behaviors to inspire the future direction. Our work can open up new valuable research directions and contribute to the research of general vision.