A New Dataset and Framework for Real-World Blurred Images Super-Resolution

TL;DR

This paper introduces a new dataset and a novel super-resolution framework specifically designed for blurred images, significantly improving performance on blurry and general images without extra inference costs.

Contribution

The paper presents ReBlurSR, a new dataset for blur images, and PBaSR, a framework with dual modules for effective super-resolution of blurred images, achieving state-of-the-art results.

Findings

PBaSR outperforms existing methods on blur and general datasets.

ReBlurSR dataset contains nearly 3000 diverse blur samples.

PBaSR improves LPIPS scores by 0.02-0.10 across benchmarks.

Abstract

Recent Blind Image Super-Resolution (BSR) methods have shown proficiency in general images. However, we find that the efficacy of recent methods obviously diminishes when employed on image data with blur, while image data with intentional blur constitute a substantial proportion of general data. To further investigate and address this issue, we developed a new super-resolution dataset specifically tailored for blur images, named the Real-world Blur-kept Super-Resolution (ReBlurSR) dataset, which consists of nearly 3000 defocus and motion blur image samples with diverse blur sizes and varying blur intensities. Furthermore, we propose a new BSR framework for blur images called Perceptual-Blur-adaptive Super-Resolution (PBaSR), which comprises two main modules: the Cross Disentanglement Module (CDM) and the Cross Fusion Module (CFM). The CDM utilizes a dual-branch parallelism to isolate conflicting blur and general data during optimization. The CFM fuses the well-optimized prior from these distinct domains cost-effectively and efficiently based on model interpolation. By integrating these two modules, PBaSR achieves commendable performance on both general and blur data without any additional inference and deployment cost and is generalizable across multiple model architectures. Rich experiments show that PBaSR achieves state-of-the-art performance across various metrics without incurring extra inference costs. Within the widely adopted LPIPS metrics, PBaSR achieves an improvement range of approximately 0.02-0.10 with diverse anchor methods and blur types, across both the ReBlurSR and multiple common general BSR benchmarks. Code here: https://github.com/Imalne/PBaSR.