Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns

TL;DR

This paper introduces a TripleGAN framework that effectively models real-world degradation patterns for super-resolution, improving the quality of reconstructed images from real-world low-resolution data.

Contribution

The novel TripleGAN approach combines domain gap reduction and domain-specific translation to better simulate real-world degradations for super-resolution tasks.

Findings

Outperforms existing methods on RealSR and DRealSR datasets

Produces sharper, less over-smoothed high-resolution images

Effectively learns real-world degradation patterns from LR images

Abstract

The training of real-world super-resolution reconstruction models heavily relies on datasets that reflect real-world degradation patterns. Extracting and modeling degradation patterns for super-resolution reconstruction using only real-world low-resolution (LR) images remains a challenging task. When synthesizing datasets to simulate real-world degradation, relying solely on degradation extraction methods fails to capture both blur and diverse noise characteristics across varying LR distributions, as well as more implicit degradations such as color gamut shifts. Conversely, domain translation alone cannot accurately approximate real-world blur characteristics due to the significant degradation domain gap between synthetic and real data. To address these challenges, we propose a novel TripleGAN framework comprising two strategically designed components: The FirstGAN primarily focuses on narrowing the domain gap in blur characteristics, while the SecondGAN performs domain-specific translation to approximate target-domain blur properties and learn additional degradation patterns. The ThirdGAN is trained on pseudo-real data generated by the FirstGAN and SecondGAN to reconstruct real-world LR images. Extensive experiments on the RealSR and DRealSR datasets demonstrate that our method exhibits clear advantages in quantitative metrics while maintaining sharp reconstructions without over-smoothing artifacts. The proposed framework effectively learns real-world degradation patterns from LR observations and synthesizes aligned datasets with corresponding degradation characteristics, thereby enabling the trained network to achieve superior performance in reconstructing high-quality SR images from real-world LR inputs.