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

arXiv:2403.02601v1 Announce Type: cross
Abstract: 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 …

abstract adaptability arxiv challenge cs.cv datasets eess.iv framework gap image leads low merging novel performance pre-training self-supervised learning supervised learning synthetic the way training type work world