Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning

For image super-resolution (SR), bridging the gap between the performance on synthetic datasets and real-world degradation scenarios remains a challenge. This work introduces a novel “Low-Res Leads the Way” (LWay) training framework, merging Supervised Pre-training with Self-supervised Learning to enhance the adaptability of SR models to real-world images. Our approach utilizes a low-resolution (LR) reconstruction network to extract degradation embeddings from LR images, merging them with super-resolved outputs for LR reconstruction. Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facili-tating fine-tuning of SR models without requiring paired high-resolution (HR) images. The integration of Discrete Wavelet Transform (DWT)further refines the focus on high-frequency details. Extensive evaluations show that our method significantly improves the generalization and de-tail restoration capabilities of SR models on unseen real-world datasets, outperforming existing methods. Our training regime is universally compatible, requiring no network architecture modifications, making it a practical solution for real-world SR applications.

1. Introduction

Image super-resolution (SR) aims to restore high-resolution (HR) images from their low-resolution (LR) or degraded counterparts. The inception of the deep-Iearning-based SR model can be traced back to SRCNN [14]. Recently, ad-vancements in deep learning models have substantially en-hanced SR performance [1, 6,8-10,12,25-27,39,51,52, 54,56], particularly in addressing specific degradation types like bicubic downsampling. Nevertheless, the efficacy of SR models is generally restricted by the degradation strate-gies employed during the training phase, posing great challenges in complex real-world applications. Figure 1.

Our proposed training method combine the benefits of supervised learning (SL) on synthetic data and self-supervised learning (SSL) on the unseen test images, achieve high quality and high fidelity SR results.