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 Selfsupervised Learning to enhance the adaptability of SR models to real-world images. Our approach utilizes a lowresolution (LR) reconstruction network to extract degradation embeddings from LR images, merging them with superresolved outputs for LR reconstruction. Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facilitating fine-tuning of SR models without requiring paired high-resolution (HR) images. The integration of Discrete Wavelet Transform (DWT) further refines the focus on highfrequency details. Extensive evaluations show that our method significantly improves the generalization and detail restoration capabilities of SR models on unseen realworld 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.